Tao Mei

Fuchen Long, Zhaofan Qiu, Yingwei Pan et al.

Motion, as the uniqueness of a video, has been critical to the development of video understanding models. Modern deep learning models leverage motion by either executing spatio-temporal 3D convolutions, factorizing 3D convolutions into spatial and temporal convolutions separately, or computing self-attention along temporal dimension. The implicit assumption behind such successes is that the feature maps across consecutive frames can be nicely aggregated. Nevertheless, the assumption may not always hold especially for the regions with large deformation. In this paper, we present a new recipe of inter-frame attention block, namely Stand-alone Inter-Frame Attention (SIFA), that novelly delves into the deformation across frames to estimate local self-attention on each spatial location. Technically, SIFA remoulds the deformable design via re-scaling the offset predictions by the difference between two frames. Taking each spatial location in the current frame as the query, the locally deformable neighbors in the next frame are regarded as the keys/values. Then, SIFA measures the similarity between query and keys as stand-alone attention to weighted average the values for temporal aggregation. We further plug SIFA block into ConvNets and Vision Transformer, respectively, to devise SIFA-Net and SIFA-Transformer. Extensive experiments conducted on four video datasets demonstrate the superiority of SIFA-Net and SIFA-Transformer as stronger backbones. More remarkably, SIFA-Transformer achieves an accuracy of 83.1% on Kinetics-400 dataset. Source code is available at \url{https://github.com/FuchenUSTC/SIFA}.

Ting Yao, Yehao Li, Yingwei Pan et al.

Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each incurs a much smaller computational complexity. However, regional information is typically only achieved at the expense of undesirable information lost owing to down-sampling. In this paper, we propose a novel Transformer architecture that aims to mitigate the cost issue, named Dual Vision Transformer (Dual-ViT). The new architecture incorporates a critical semantic pathway that can more efficiently compress token vectors into global semantics with reduced order of complexity. Such compressed global semantics then serve as useful prior information in learning finer pixel level details, through another constructed pixel pathway. The semantic pathway and pixel pathway are then integrated together and are jointly trained, spreading the enhanced self-attention information in parallel through both of the pathways. Dual-ViT is henceforth able to reduce the computational complexity without compromising much accuracy. We empirically demonstrate that Dual-ViT provides superior accuracy than SOTA Transformer architectures with reduced training complexity. Source code is available at \url{https://github.com/YehLi/ImageNetModel}.

Yehao Li, Yingwei Pan, Ting Yao et al.

Comprehending the rich semantics in an image and ordering them in linguistic order are essential to compose a visually-grounded and linguistically coherent description for image captioning. Modern techniques commonly capitalize on a pre-trained object detector/classifier to mine the semantics in an image, while leaving the inherent linguistic ordering of semantics under-exploited. In this paper, we propose a new recipe of Transformer-style structure, namely Comprehending and Ordering Semantics Networks (COS-Net), that novelly unifies an enriched semantic comprehending and a learnable semantic ordering processes into a single architecture. Technically, we initially utilize a cross-modal retrieval model to search the relevant sentences of each image, and all words in the searched sentences are taken as primary semantic cues. Next, a novel semantic comprehender is devised to filter out the irrelevant semantic words in primary semantic cues, and meanwhile infer the missing relevant semantic words visually grounded in the image. After that, we feed all the screened and enriched semantic words into a semantic ranker, which learns to allocate all semantic words in linguistic order as humans. Such sequence of ordered semantic words are further integrated with visual tokens of images to trigger sentence generation. Empirical evidences show that COS-Net clearly surpasses the state-of-the-art approaches on COCO and achieves to-date the best CIDEr score of 141.1% on Karpathy test split. Source code is available at \url{https://github.com/YehLi/xmodaler/tree/master/configs/image_caption/cosnet}.

Fuchen Long, Ting Yao, Zhaofan Qiu et al.

The leverage of large volumes of web videos paired with the searched queries or surrounding texts (e.g., title) offers an economic and extensible alternative to supervised video representation learning. Nevertheless, modeling such weakly visual-textual connection is not trivial due to query polysemy (i.e., many possible meanings for a query) and text isomorphism (i.e., same syntactic structure of different text). In this paper, we introduce a new design of mutual calibration between query and text to boost weakly-supervised video representation learning. Specifically, we present Bi-Calibration Networks (BCN) that novelly couples two calibrations to learn the amendment from text to query and vice versa. Technically, BCN executes clustering on all the titles of the videos searched by an identical query and takes the centroid of each cluster as a text prototype. The query vocabulary is built directly on query words. The video-to-text/video-to-query projections over text prototypes/query vocabulary then start the text-to-query or query-to-text calibration to estimate the amendment to query or text. We also devise a selection scheme to balance the two corrections. Two large-scale web video datasets paired with query and title for each video are newly collected for weakly-supervised video representation learning, which are named as YOVO-3M and YOVO-10M, respectively. The video features of BCN learnt on 3M web videos obtain superior results under linear model protocol on downstream tasks. More remarkably, BCN trained on the larger set of 10M web videos with further fine-tuning leads to 1.6%, and 1.8% gains in top-1 accuracy on Kinetics-400, and Something-Something V2 datasets over the state-of-the-art TDN, and ACTION-Net methods with ImageNet pre-training. Source code and datasets are available at \url{https://github.com/FuchenUSTC/BCN}.

Haibo Yang, Yang Chen, Yingwei Pan et al.

Despite having tremendous progress in image-to-3D generation, existing methods still struggle to produce multi-view consistent images with high-resolution textures in detail, especially in the paradigm of 2D diffusion that lacks 3D awareness. In this work, we present High-resolution Image-to-3D model (Hi3D), a new video diffusion based paradigm that redefines a single image to multi-view images as 3D-aware sequential image generation (i.e., orbital video generation). This methodology delves into the underlying temporal consistency knowledge in video diffusion model that generalizes well to geometry consistency across multiple views in 3D generation. Technically, Hi3D first empowers the pre-trained video diffusion model with 3D-aware prior (camera pose condition), yielding multi-view images with low-resolution texture details. A 3D-aware video-to-video refiner is learnt to further scale up the multi-view images with high-resolution texture details. Such high-resolution multi-view images are further augmented with novel views through 3D Gaussian Splatting, which are finally leveraged to obtain high-fidelity meshes via 3D reconstruction. Extensive experiments on both novel view synthesis and single view reconstruction demonstrate that our Hi3D manages to produce superior multi-view consistency images with highly-detailed textures. Source code and data are available at \url{https://github.com/yanghb22-fdu/Hi3D-Official}.

Yiheng Zhang, Ting Yao, Zhaofan Qiu et al.

Multi-scale learning frameworks have been regarded as a capable class of models to boost semantic segmentation. The problem nevertheless is not trivial especially for the real-world deployments, which often demand high efficiency in inference latency. In this paper, we thoroughly analyze the design of convolutional blocks (the type of convolutions and the number of channels in convolutions), and the ways of interactions across multiple scales, all from lightweight standpoint for semantic segmentation. With such in-depth comparisons, we conclude three principles, and accordingly devise Lightweight and Progressively-Scalable Networks (LPS-Net) that novelly expands the network complexity in a greedy manner. Technically, LPS-Net first capitalizes on the principles to build a tiny network. Then, LPS-Net progressively scales the tiny network to larger ones by expanding a single dimension (the number of convolutional blocks, the number of channels, or the input resolution) at one time to meet the best speed/accuracy tradeoff. Extensive experiments conducted on three datasets consistently demonstrate the superiority of LPS-Net over several efficient semantic segmentation methods. More remarkably, our LPS-Net achieves 73.4% mIoU on Cityscapes test set, with the speed of 413.5FPS on an NVIDIA GTX 1080Ti, leading to a performance improvement by 1.5% and a 65% speed-up against the state-of-the-art STDC. Code is available at \url{https://github.com/YihengZhang-CV/LPS-Net}.

Fuchen Long, Zhaofan Qiu, Yingwei Pan et al.

Video temporal dynamics is conventionally modeled with 3D spatial-temporal kernel or its factorized version comprised of 2D spatial kernel and 1D temporal kernel. The modeling power, nevertheless, is limited by the fixed window size and static weights of a kernel along the temporal dimension. The pre-determined kernel size severely limits the temporal receptive fields and the fixed weights treat each spatial location across frames equally, resulting in sub-optimal solution for long-range temporal modeling in natural scenes. In this paper, we present a new recipe of temporal feature learning, namely Dynamic Temporal Filter (DTF), that novelly performs spatial-aware temporal modeling in frequency domain with large temporal receptive field. Specifically, DTF dynamically learns a specialized frequency filter for every spatial location to model its long-range temporal dynamics. Meanwhile, the temporal feature of each spatial location is also transformed into frequency feature spectrum via 1D Fast Fourier Transform (FFT). The spectrum is modulated by the learnt frequency filter, and then transformed back to temporal domain with inverse FFT. In addition, to facilitate the learning of frequency filter in DTF, we perform frame-wise aggregation to enhance the primary temporal feature with its temporal neighbors by inter-frame correlation. It is feasible to plug DTF block into ConvNets and Transformer, yielding DTF-Net and DTF-Transformer. Extensive experiments conducted on three datasets demonstrate the superiority of our proposals. More remarkably, DTF-Transformer achieves an accuracy of 83.5% on Kinetics-400 dataset. Source code is available at \url{https://github.com/FuchenUSTC/DTF}.

Zhaofan Qiu, Ting Yao, Chong-Wah Ngo et al.

Convolutional Neural Networks (CNNs) have been regarded as the go-to models for visual recognition. More recently, convolution-free networks, based on multi-head self-attention (MSA) or multi-layer perceptrons (MLPs), become more and more popular. Nevertheless, it is not trivial when utilizing these newly-minted networks for video recognition due to the large variations and complexities in video data. In this paper, we present MLP-3D networks, a novel MLP-like 3D architecture for video recognition. Specifically, the architecture consists of MLP-3D blocks, where each block contains one MLP applied across tokens (i.e., token-mixing MLP) and one MLP applied independently to each token (i.e., channel MLP). By deriving the novel grouped time mixing (GTM) operations, we equip the basic token-mixing MLP with the ability of temporal modeling. GTM divides the input tokens into several temporal groups and linearly maps the tokens in each group with the shared projection matrix. Furthermore, we devise several variants of GTM with different grouping strategies, and compose each variant in different blocks of MLP-3D network by greedy architecture search. Without the dependence on convolutions or attention mechanisms, our MLP-3D networks achieves 68.5\%/81.4\% top-1 accuracy on Something-Something V2 and Kinetics-400 datasets, respectively. Despite with fewer computations, the results are comparable to state-of-the-art widely-used 3D CNNs and video transformers. Source code is available at https://github.com/ZhaofanQiu/MLP-3D.

Zhaofan Qiu, Yehao Li, Yu Wang et al.

In this paper, we propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net. The embedded ``Selective Position Encoding (SPE)'' procedure relies on an attention mechanism that can effectively attend to the underlying rotation condition of the input. Such encoded rotation condition then determines which part of the network parameters to be focused on, and is shown to efficiently help reduce the degree of freedom of the optimization during training. This mechanism henceforth can better leverage the rotation augmentations through reduced training difficulties, making SPE-Net robust against rotated data both during training and testing. The new findings in our paper also urge us to rethink the relationship between the extracted rotation information and the actual test accuracy. Intriguingly, we reveal evidences that by locally encoding the rotation information through SPE-Net, the rotation-invariant features are still of critical importance in benefiting the test samples without any actual global rotation. We empirically demonstrate the merits of the SPE-Net and the associated hypothesis on four benchmarks, showing evident improvements on both rotated and unrotated test data over SOTA methods. Source code is available at https://github.com/ZhaofanQiu/SPE-Net.

Mohan Zhou, Yalong Bai, Wei Zhang et al.

A reliable and comprehensive evaluation metric that aligns with manual preference assessments is crucial for conversational head video synthesis methods development. Existing quantitative evaluations often fail to capture the full complexity of human preference, as they only consider limited evaluation dimensions. Qualitative evaluations and user studies offer a solution but are time-consuming and labor-intensive. This limitation hinders the advancement of conversational head generation algorithms and systems. In this paper, we propose a novel learning-based evaluation metric named Preference Score (PS) for fitting human preference according to the quantitative evaluations across different dimensions. PS can serve as a quantitative evaluation without the need for human annotation. Experimental results validate the superiority of Preference Score in aligning with human perception, and also demonstrate robustness and generalizability to unseen data, making it a valuable tool for advancing conversation head generation. We expect this metric could facilitate new advances in conversational head generation. Project Page: https://https://github.com/dc3ea9f/PreferenceScore.

Yu Sun, Qian Bao, Wu Liu et al.

Although the estimation of 3D human pose and shape (HPS) is rapidly progressing, current methods still cannot reliably estimate moving humans in global coordinates, which is critical for many applications. This is particularly challenging when the camera is also moving, entangling human and camera motion. To address these issues, we adopt a novel 5D representation (space, time, and identity) that enables end-to-end reasoning about people in scenes. Our method, called TRACE, introduces several novel architectural components. Most importantly, it uses two new "maps" to reason about the 3D trajectory of people over time in camera, and world, coordinates. An additional memory unit enables persistent tracking of people even during long occlusions. TRACE is the first one-stage method to jointly recover and track 3D humans in global coordinates from dynamic cameras. By training it end-to-end, and using full image information, TRACE achieves state-of-the-art performance on tracking and HPS benchmarks. The code and dataset are released for research purposes.

Lianli Gao, Pengpeng Zeng, Jingkuan Song et al.

To date, visual question answering (VQA) (i.e., image QA and video QA) is still a holy grail in vision and language understanding, especially for video QA. Compared with image QA that focuses primarily on understanding the associations between image region-level details and corresponding questions, video QA requires a model to jointly reason across both spatial and long-range temporal structures of a video as well as text to provide an accurate answer. In this paper, we specifically tackle the problem of video QA by proposing a Structured Two-stream Attention network, namely STA, to answer a free-form or open-ended natural language question about the content of a given video. First, we infer rich long-range temporal structures in videos using our structured segment component and encode text features. Then, our structured two-stream attention component simultaneously localizes important visual instance, reduces the influence of background video and focuses on the relevant text. Finally, the structured two-stream fusion component incorporates different segments of query and video aware context representation and infers the answers. Experiments on the large-scale video QA dataset \textit{TGIF-QA} show that our proposed method significantly surpasses the best counterpart (i.e., with one representation for the video input) by 13.0%, 13.5%, 11.0% and 0.3 for Action, Trans., TrameQA and Count tasks. It also outperforms the best competitor (i.e., with two representations) on the Action, Trans., TrameQA tasks by 4.1%, 4.7%, and 5.1%.

Jie Ma, Yalong Bai, Bineng Zhong et al.

Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having good success, the literature seldom explores the explainability of vision transformer, and there is no clear picture of how the attention mechanism with respect to the correlation across comprehensive patches will impact the performance and what is the further potential. In this work, we propose a novel explainable visualization approach to analyze and interpret the crucial attention interactions among patches for vision transformer. Specifically, we first introduce a quantification indicator to measure the impact of patch interaction and verify such quantification on attention window design and indiscriminative patches removal. Then, we exploit the effective responsive field of each patch in ViT and devise a window-free transformer architecture accordingly. Extensive experiments on ImageNet demonstrate that the exquisitely designed quantitative method is shown able to facilitate ViT model learning, leading the top-1 accuracy by 4.28% at most. Moreover, the results on downstream fine-grained recognition tasks further validate the generalization of our proposal.

Sanqing Qu, Yingwei Pan, Guang Chen et al.

Deep neural networks (DNNs) usually fail to generalize well to outside of distribution (OOD) data, especially in the extreme case of single domain generalization (single-DG) that transfers DNNs from single domain to multiple unseen domains. Existing single-DG techniques commonly devise various data-augmentation algorithms, and remould the multi-source domain generalization methodology to learn domain-generalized (semantic) features. Nevertheless, these methods are typically modality-specific, thereby being only applicable to one single modality (e.g., image). In contrast, we target a versatile Modality-Agnostic Debiasing (MAD) framework for single-DG, that enables generalization for different modalities. Technically, MAD introduces a novel two-branch classifier: a biased-branch encourages the classifier to identify the domain-specific (superficial) features, and a general-branch captures domain-generalized features based on the knowledge from biased-branch. Our MAD is appealing in view that it is pluggable to most single-DG models. We validate the superiority of our MAD in a variety of single-DG scenarios with different modalities, including recognition on 1D texts, 2D images, 3D point clouds, and semantic segmentation on 2D images. More remarkably, for recognition on 3D point clouds and semantic segmentation on 2D images, MAD improves DSU by 2.82\% and 1.5\% in accuracy and mIOU.

Xiaodong Chen, Xinchen Liu, Wu Liu et al.

Action recognition from videos, i.e., classifying a video into one of the pre-defined action types, has been a popular topic in the communities of artificial intelligence, multimedia, and signal processing. However, existing methods usually consider an input video as a whole and learn models, e.g., Convolutional Neural Networks (CNNs), with coarse video-level class labels. These methods can only output an action class for the video, but cannot provide fine-grained and explainable cues to answer why the video shows a specific action. Therefore, researchers start to focus on a new task, Part-level Action Parsing (PAP), which aims to not only predict the video-level action but also recognize the frame-level fine-grained actions or interactions of body parts for each person in the video. To this end, we propose a coarse-to-fine framework for this challenging task. In particular, our framework first predicts the video-level class of the input video, then localizes the body parts and predicts the part-level action. Moreover, to balance the accuracy and computation in part-level action parsing, we propose to recognize the part-level actions by segment-level features. Furthermore, to overcome the ambiguity of body parts, we propose a pose-guided positional embedding method to accurately localize body parts. Through comprehensive experiments on a large-scale dataset, i.e., Kinetics-TPS, our framework achieves state-of-the-art performance and outperforms existing methods over a 31.10% ROC score.

Xiaodong Chen, Wu Liu, Xinchen Liu et al.

Recognizing human actions from point cloud videos has attracted tremendous attention from both academia and industry due to its wide applications like automatic driving, robotics, and so on. However, current methods for point cloud action recognition usually require a huge amount of data with manual annotations and a complex backbone network with high computation costs, which makes it impractical for real-world applications. Therefore, this paper considers the task of semi-supervised point cloud action recognition. We propose a Masked Pseudo-Labeling autoEncoder (\textbf{MAPLE}) framework to learn effective representations with much fewer annotations for point cloud action recognition. In particular, we design a novel and efficient \textbf{De}coupled \textbf{s}patial-\textbf{t}emporal Trans\textbf{Former} (\textbf{DestFormer}) as the backbone of MAPLE. In DestFormer, the spatial and temporal dimensions of the 4D point cloud videos are decoupled to achieve efficient self-attention for learning both long-term and short-term features. Moreover, to learn discriminative features from fewer annotations, we design a masked pseudo-labeling autoencoder structure to guide the DestFormer to reconstruct features of masked frames from the available frames. More importantly, for unlabeled data, we exploit the pseudo-labels from the classification head as the supervision signal for the reconstruction of features from the masked frames. Finally, comprehensive experiments demonstrate that MAPLE achieves superior results on three public benchmarks and outperforms the state-of-the-art method by 8.08\% accuracy on the MSR-Action3D dataset.

Yi Tan, Zhaofan Qiu, Yanbin Hao et al.

The recent advances in Convolutional Neural Networks (CNNs) and Vision Transformers have convincingly demonstrated high learning capability for video action recognition on large datasets. Nevertheless, deep models often suffer from the overfitting effect on small-scale datasets with a limited number of training videos. A common solution is to exploit the existing image augmentation strategies for each frame individually including Mixup, Cutmix, and RandAugment, which are not particularly optimized for video data. In this paper, we propose a novel video augmentation strategy named Selective Volume Mixup (SV-Mix) to improve the generalization ability of deep models with limited training videos. SV-Mix devises a learnable selective module to choose the most informative volumes from two videos and mixes the volumes up to achieve a new training video. Technically, we propose two new modules, i.e., a spatial selective module to select the local patches for each spatial position, and a temporal selective module to mix the entire frames for each timestamp and maintain the spatial pattern. At each time, we randomly choose one of the two modules to expand the diversity of training samples. The selective modules are jointly optimized with the video action recognition framework to find the optimal augmentation strategy. We empirically demonstrate the merits of the SV-Mix augmentation on a wide range of video action recognition benchmarks and consistently boot the performances of both CNN-based and transformer-based models.

Yang Luo, Yiheng Zhang, Zhaofan Qiu et al.

The emergence of text-to-image generation models has led to the recognition that image enhancement, performed as post-processing, would significantly improve the visual quality of the generated images. Exploring diffusion models to enhance the generated images nevertheless is not trivial and necessitates to delicately enrich plentiful details while preserving the visual appearance of key content in the original image. In this paper, we propose a novel framework, namely FreeEnhance, for content-consistent image enhancement using the off-the-shelf image diffusion models. Technically, FreeEnhance is a two-stage process that firstly adds random noise to the input image and then capitalizes on a pre-trained image diffusion model (i.e., Latent Diffusion Models) to denoise and enhance the image details. In the noising stage, FreeEnhance is devised to add lighter noise to the region with higher frequency to preserve the high-frequent patterns (e.g., edge, corner) in the original image. In the denoising stage, we present three target properties as constraints to regularize the predicted noise, enhancing images with high acutance and high visual quality. Extensive experiments conducted on the HPDv2 dataset demonstrate that our FreeEnhance outperforms the state-of-the-art image enhancement models in terms of quantitative metrics and human preference. More remarkably, FreeEnhance also shows higher human preference compared to the commercial image enhancement solution of Magnific AI.

Mohan Zhou, Yalong Bai, Wei Zhang et al.

Dynamically synthesizing talking speech that actively responds to a listening head is critical during the face-to-face interaction. For example, the speaker could take advantage of the listener's facial expression to adjust the tones, stressed syllables, or pauses. In this work, we present a new visual-aware text-to-speech (VA-TTS) task to synthesize speech conditioned on both textual inputs and sequential visual feedback (e.g., nod, smile) of the listener in face-to-face communication. Different from traditional text-to-speech, VA-TTS highlights the impact of visual modality. On this newly-minted task, we devise a baseline model to fuse phoneme linguistic information and listener visual signals for speech synthesis. Extensive experiments on multimodal conversation dataset ViCo-X verify our proposal for generating more natural audio with scenario-appropriate rhythm and prosody.

Peipei Li, Xing Cui, Yibo Hu et al.

Point cloud analysis faces computational system overhead, limiting its application on mobile or edge devices. Directly employing small models may result in a significant drop in performance since it is difficult for a small model to adequately capture local structure and global shape information simultaneously, which are essential clues for point cloud analysis. This paper explores feature distillation for lightweight point cloud models. To mitigate the semantic gap between the lightweight student and the cumbersome teacher, we propose bidirectional knowledge reconfiguration (BKR) to distill informative contextual knowledge from the teacher to the student. Specifically, a top-down knowledge reconfiguration and a bottom-up knowledge reconfiguration are developed to inherit diverse local structure information and consistent global shape knowledge from the teacher, respectively. However, due to the farthest point sampling in most point cloud models, the intermediate features between teacher and student are misaligned, deteriorating the feature distillation performance. To eliminate it, we propose a feature mover's distance (FMD) loss based on optimal transportation, which can measure the distance between unordered point cloud features effectively. Extensive experiments conducted on shape classification, part segmentation, and semantic segmentation benchmarks demonstrate the universality and superiority of our method.

Fuchen Long, Zhaofan Qiu, Ting Yao et al.

The recent innovations and breakthroughs in diffusion models have significantly expanded the possibilities of generating high-quality videos for the given prompts. Most existing works tackle the single-scene scenario with only one video event occurring in a single background. Extending to generate multi-scene videos nevertheless is not trivial and necessitates to nicely manage the logic in between while preserving the consistent visual appearance of key content across video scenes. In this paper, we propose a novel framework, namely VideoStudio, for consistent-content and multi-scene video generation. Technically, VideoStudio leverages Large Language Models (LLM) to convert the input prompt into comprehensive multi-scene script that benefits from the logical knowledge learnt by LLM. The script for each scene includes a prompt describing the event, the foreground/background entities, as well as camera movement. VideoStudio identifies the common entities throughout the script and asks LLM to detail each entity. The resultant entity description is then fed into a text-to-image model to generate a reference image for each entity. Finally, VideoStudio outputs a multi-scene video by generating each scene video via a diffusion process that takes the reference images, the descriptive prompt of the event and camera movement into account. The diffusion model incorporates the reference images as the condition and alignment to strengthen the content consistency of multi-scene videos. Extensive experiments demonstrate that VideoStudio outperforms the SOTA video generation models in terms of visual quality, content consistency, and user preference. Source code is available at \url{https://github.com/FuchenUSTC/VideoStudio}.

Rui Li, Yiheng Zhang, Zhaofan Qiu et al.

Motion, as the most distinct phenomenon in a video to involve the changes over time, has been unique and critical to the development of video representation learning. In this paper, we ask the question: how important is the motion particularly for self-supervised video representation learning. To this end, we compose a duet of exploiting the motion for data augmentation and feature learning in the regime of contrastive learning. Specifically, we present a Motion-focused Contrastive Learning (MCL) method that regards such duet as the foundation. On one hand, MCL capitalizes on optical flow of each frame in a video to temporally and spatially sample the tubelets (i.e., sequences of associated frame patches across time) as data augmentations. On the other hand, MCL further aligns gradient maps of the convolutional layers to optical flow maps from spatial, temporal and spatio-temporal perspectives, in order to ground motion information in feature learning. Extensive experiments conducted on R(2+1)D backbone demonstrate the effectiveness of our MCL. On UCF101, the linear classifier trained on the representations learnt by MCL achieves 81.91% top-1 accuracy, outperforming ImageNet supervised pre-training by 6.78%. On Kinetics-400, MCL achieves 66.62% top-1 accuracy under the linear protocol. Code is available at https://github.com/YihengZhang-CV/MCL-Motion-Focused-Contrastive-Learning.

Zhaofan Qiu, Ting Yao, Chong-Wah Ngo et al.

It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning process starts from learning 3D ConvNets using short video clips and then is followed by learning long-term temporal dependency using lengthy clips, while gradually decaying the learning rate from high to low as training progresses. The fact that such process comes along with several heuristic settings motivates the study to seek an optimal "path" to automate the entire training. In this paper, we decompose the path into a series of training "states" and specify the hyper-parameters, e.g., learning rate and the length of input clips, in each state. The estimation of the knee point on the performance-epoch curve triggers the transition from one state to another. We perform dynamic programming over all the candidate states to plan the optimal permutation of states, i.e., optimization path. Furthermore, we devise a new 3D ConvNets with a unique design of dual-head classifier to improve spatial and temporal discrimination. Extensive experiments on seven public video recognition benchmarks demonstrate the advantages of our proposal. With the optimization planning, our 3D ConvNets achieves superior results when comparing to the state-of-the-art recognition methods. More remarkably, we obtain the top-1 accuracy of 80.5% and 82.7% on Kinetics-400 and Kinetics-600 datasets, respectively. Source code is available at https://github.com/ZhaofanQiu/Optimization-Planning-for-3D-ConvNets.

Yu Wang, Jingyang Lin, Jingjing Zou et al.

Our work reveals a structured shortcoming of the existing mainstream self-supervised learning methods. Whereas self-supervised learning frameworks usually take the prevailing perfect instance level invariance hypothesis for granted, we carefully investigate the pitfalls behind. Particularly, we argue that the existing augmentation pipeline for generating multiple positive views naturally introduces out-of-distribution (OOD) samples that undermine the learning of the downstream tasks. Generating diverse positive augmentations on the input does not always pay off in benefiting downstream tasks. To overcome this inherent deficiency, we introduce a lightweight latent variable model UOTA, targeting the view sampling issue for self-supervised learning. UOTA adaptively searches for the most important sampling region to produce views, and provides viable choice for outlier-robust self-supervised learning approaches. Our method directly generalizes to many mainstream self-supervised learning approaches, regardless of the loss's nature contrastive or not. We empirically show UOTA's advantage over the state-of-the-art self-supervised paradigms with evident margin, which well justifies the existence of the OOD sample issue embedded in the existing approaches. Especially, we theoretically prove that the merits of the proposal boil down to guaranteed estimator variance and bias reduction. Code is available: at https://github.com/ssl-codelab/uota.

Hangtong Wu, Dan Zen, Yibo Hu et al.

Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks. Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance, which limits the generalization ability of FAS model. In this paper, we propose Dual Spoof Disentanglement Generation (DSDG) framework to tackle this challenge by "anti-spoofing via generation". Depending on the interpretable factorized latent disentanglement in Variational Autoencoder (VAE), DSDG learns a joint distribution of the identity representation and the spoofing pattern representation in the latent space. Then, large-scale paired live and spoofing images can be generated from random noise to boost the diversity of the training set. However, some generated face images are partially distorted due to the inherent defect of VAE. Such noisy samples are hard to predict precise depth values, thus may obstruct the widely-used depth supervised optimization. To tackle this issue, we further introduce a lightweight Depth Uncertainty Module (DUM), which alleviates the adverse effects of noisy samples by depth uncertainty learning. DUM is developed without extra-dependency, thus can be flexibly integrated with any depth supervised network for face anti-spoofing. We evaluate the effectiveness of the proposed method on five popular benchmarks and achieve state-of-the-art results under both intra- and inter- test settings. The codes are available at https://github.com/JDAI-CV/FaceX-Zoo/tree/main/addition_module/DSDG.

Yehao Li, Yingwei Pan, Jingwen Chen et al.

With the rise and development of deep learning over the past decade, there has been a steady momentum of innovation and breakthroughs that convincingly push the state-of-the-art of cross-modal analytics between vision and language in multimedia field. Nevertheless, there has not been an open-source codebase in support of training and deploying numerous neural network models for cross-modal analytics in a unified and modular fashion. In this work, we propose X-modaler -- a versatile and high-performance codebase that encapsulates the state-of-the-art cross-modal analytics into several general-purpose stages (e.g., pre-processing, encoder, cross-modal interaction, decoder, and decode strategy). Each stage is empowered with the functionality that covers a series of modules widely adopted in state-of-the-arts and allows seamless switching in between. This way naturally enables a flexible implementation of state-of-the-art algorithms for image captioning, video captioning, and vision-language pre-training, aiming to facilitate the rapid development of research community. Meanwhile, since the effective modular designs in several stages (e.g., cross-modal interaction) are shared across different vision-language tasks, X-modaler can be simply extended to power startup prototypes for other tasks in cross-modal analytics, including visual question answering, visual commonsense reasoning, and cross-modal retrieval. X-modaler is an Apache-licensed codebase, and its source codes, sample projects and pre-trained models are available on-line: https://github.com/YehLi/xmodaler.

Yehao Li, Yingwei Pan, Ting Yao et al.

Despite having impressive vision-language (VL) pretraining with BERT-based encoder for VL understanding, the pretraining of a universal encoder-decoder for both VL understanding and generation remains challenging. The difficulty originates from the inherently different peculiarities of the two disciplines, e.g., VL understanding tasks capitalize on the unrestricted message passing across modalities, while generation tasks only employ visual-to-textual message passing. In this paper, we start with a two-stream decoupled design of encoder-decoder structure, in which two decoupled cross-modal encoder and decoder are involved to separately perform each type of proxy tasks, for simultaneous VL understanding and generation pretraining. Moreover, for VL pretraining, the dominant way is to replace some input visual/word tokens with mask tokens and enforce the multi-modal encoder/decoder to reconstruct the original tokens, but no mask token is involved when fine-tuning on downstream tasks. As an alternative, we propose a primary scheduled sampling strategy that elegantly mitigates such discrepancy via pretraining encoder-decoder in a two-pass manner. Extensive experiments demonstrate the compelling generalizability of our pretrained encoder-decoder by fine-tuning on four VL understanding and generation downstream tasks. Source code is available at \url{https://github.com/YehLi/TDEN}.

Jun Wang, Yinglu Liu, Yibo Hu et al.

Deep learning based face recognition has achieved significant progress in recent years. Yet, the practical model production and further research of deep face recognition are in great need of corresponding public support. For example, the production of face representation network desires a modular training scheme to consider the proper choice from various candidates of state-of-the-art backbone and training supervision subject to the real-world face recognition demand; for performance analysis and comparison, the standard and automatic evaluation with a bunch of models on multiple benchmarks will be a desired tool as well; besides, a public groundwork is welcomed for deploying the face recognition in the shape of holistic pipeline. Furthermore, there are some newly-emerged challenges, such as the masked face recognition caused by the recent world-wide COVID-19 pandemic, which draws increasing attention in practical applications. A feasible and elegant solution is to build an easy-to-use unified framework to meet the above demands. To this end, we introduce a novel open-source framework, named FaceX-Zoo, which is oriented to the research-development community of face recognition. Resorting to the highly modular and scalable design, FaceX-Zoo provides a training module with various supervisory heads and backbones towards state-of-the-art face recognition, as well as a standardized evaluation module which enables to evaluate the models in most of the popular benchmarks just by editing a simple configuration. Also, a simple yet fully functional face SDK is provided for the validation and primary application of the trained models. Rather than including as many as possible of the prior techniques, we enable FaceX-Zoo to easily upgrade and extend along with the development of face related domains. The source code and models are available at https://github.com/JDAI-CV/FaceX-Zoo.

Qi Cai, Yu Wang, Yingwei Pan et al.

This paper explores useful modifications of the recent development in contrastive learning via novel probabilistic modeling. We derive a particular form of contrastive loss named Joint Contrastive Learning (JCL). JCL implicitly involves the simultaneous learning of an infinite number of query-key pairs, which poses tighter constraints when searching for invariant features. We derive an upper bound on this formulation that allows analytical solutions in an end-to-end training manner. While JCL is practically effective in numerous computer vision applications, we also theoretically unveil the certain mechanisms that govern the behavior of JCL. We demonstrate that the proposed formulation harbors an innate agency that strongly favors similarity within each instance-specific class, and therefore remains advantageous when searching for discriminative features among distinct instances. We evaluate these proposals on multiple benchmarks, demonstrating considerable improvements over existing algorithms. Code is publicly available at: https://github.com/caiqi/Joint-Contrastive-Learning.

Fuchen Long, Ting Yao, Zhaofan Qiu et al.

With the knowledge of action moments (i.e., trimmed video clips that each contains an action instance), humans could routinely localize an action temporally in an untrimmed video. Nevertheless, most practical methods still require all training videos to be labeled with temporal annotations (action category and temporal boundary) and develop the models in a fully-supervised manner, despite expensive labeling efforts and inapplicable to new categories. In this paper, we introduce a new design of transfer learning type to learn action localization for a large set of action categories, but only on action moments from the categories of interest and temporal annotations of untrimmed videos from a small set of action classes. Specifically, we present Action Herald Networks (AherNet) that integrate such design into an one-stage action localization framework. Technically, a weight transfer function is uniquely devised to build the transformation between classification of action moments or foreground video segments and action localization in synthetic contextual moments or untrimmed videos. The context of each moment is learnt through the adversarial mechanism to differentiate the generated features from those of background in untrimmed videos. Extensive experiments are conducted on the learning both across the splits of ActivityNet v1.3 and from THUMOS14 to ActivityNet v1.3. Our AherNet demonstrates the superiority even comparing to most fully-supervised action localization methods. More remarkably, we train AherNet to localize actions from 600 categories on the leverage of action moments in Kinetics-600 and temporal annotations from 200 classes in ActivityNet v1.3. Source code and data are available at \url{https://github.com/FuchenUSTC/AherNet}.

Boqiang Xu, Lingxiao He, Xingyu Liao et al.

Person re-identification (Re-ID) aims at retrieving an input person image from a set of images captured by multiple cameras. Although recent Re-ID methods have made great success, most of them extract features in terms of the attributes of clothing (e.g., color, texture). However, it is common for people to wear black clothes or be captured by surveillance systems in low light illumination, in which cases the attributes of the clothing are severely missing. We call this problem the Black Re-ID problem. To solve this problem, rather than relying on the clothing information, we propose to exploit head-shoulder features to assist person Re-ID. The head-shoulder adaptive attention network (HAA) is proposed to learn the head-shoulder feature and an innovative ensemble method is designed to enhance the generalization of our model. Given the input person image, the ensemble method would focus on the head-shoulder feature by assigning a larger weight if the individual insides the image is in black clothing. Due to the lack of a suitable benchmark dataset for studying the Black Re-ID problem, we also contribute the first Black-reID dataset, which contains 1274 identities in training set. Extensive evaluations on the Black-reID, Market1501 and DukeMTMC-reID datasets show that our model achieves the best result compared with the state-of-the-art Re-ID methods on both Black and conventional Re-ID problems. Furthermore, our method is also proved to be effective in dealing with person Re-ID in similar clothing. Our code and dataset are avaliable on https://github.com/xbq1994/.

Gusi Te, Yinglu Liu, Wei Hu et al.

Face parsing infers a pixel-wise label to each facial component, which has drawn much attention recently. Previous methods have shown their efficiency in face parsing, which however overlook the correlation among different face regions. The correlation is a critical clue about the facial appearance, pose, expression etc., and should be taken into account for face parsing. To this end, we propose to model and reason the region-wise relations by learning graph representations, and leverage the edge information between regions for optimized abstraction. Specifically, we encode a facial image onto a global graph representation where a collection of pixels ("regions") with similar features are projected to each vertex. Our model learns and reasons over relations between the regions by propagating information across vertices on the graph. Furthermore, we incorporate the edge information to aggregate the pixel-wise features onto vertices, which emphasizes on the features around edges for fine segmentation along edges. The finally learned graph representation is projected back to pixel grids for parsing. Experiments demonstrate that our model outperforms state-of-the-art methods on the widely used Helen dataset, and also exhibits the superior performance on the large-scale CelebAMask-HQ and LaPa dataset. The code is available at https://github.com/tegusi/EAGRNet.

Haoran Wang, Tong Shen, Wei Zhang et al.

Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain. However, most existing methods attempt to perform the alignment from a holistic view, ignoring the underlying class-level data structure in the target domain. To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains. We adopt a fine-grained domain discriminator that not only plays as a domain distinguisher, but also differentiates domains at class level. The traditional binary domain labels are also generalized to domain encodings as the supervision signal to guide the fine-grained feature alignment. An analysis with Class Center Distance (CCD) validates that our fine-grained adversarial strategy achieves better class-level alignment compared to other state-of-the-art methods. Our method is easy to implement and its effectiveness is evaluated on three classical domain adaptation tasks, i.e., GTA5 to Cityscapes, SYNTHIA to Cityscapes and Cityscapes to Cross-City. Large performance gains show that our method outperforms other global feature alignment based and class-wise alignment based counterparts. The code is publicly available at https://github.com/JDAI-CV/FADA.

Jiajun Deng, Yingwei Pan, Ting Yao et al.

Single shot detectors that are potentially faster and simpler than two-stage detectors tend to be more applicable to object detection in videos. Nevertheless, the extension of such object detectors from image to video is not trivial especially when appearance deterioration exists in videos, \emph{e.g.}, motion blur or occlusion. A valid question is how to explore temporal coherence across frames for boosting detection. In this paper, we propose to address the problem by enhancing per-frame features through aggregation of neighboring frames. Specifically, we present Single Shot Video Object Detector (SSVD) -- a new architecture that novelly integrates feature aggregation into a one-stage detector for object detection in videos. Technically, SSVD takes Feature Pyramid Network (FPN) as backbone network to produce multi-scale features. Unlike the existing feature aggregation methods, SSVD, on one hand, estimates the motion and aggregates the nearby features along the motion path, and on the other, hallucinates features by directly sampling features from the adjacent frames in a two-stream structure. Extensive experiments are conducted on ImageNet VID dataset, and competitive results are reported when comparing to state-of-the-art approaches. More remarkably, for $448 \times 448$ input, SSVD achieves 79.2% mAP on ImageNet VID, by processing one frame in 85 ms on an Nvidia Titan X Pascal GPU. The code is available at \url{https://github.com/ddjiajun/SSVD}.

Lingxiao He, Xingyu Liao, Wu Liu et al.

General Instance Re-identification is a very important task in the computer vision, which can be widely used in many practical applications, such as person/vehicle re-identification, face recognition, wildlife protection, commodity tracing, and snapshop, etc.. To meet the increasing application demand for general instance re-identification, we present FastReID as a widely used software system in JD AI Research. In FastReID, highly modular and extensible design makes it easy for the researcher to achieve new research ideas. Friendly manageable system configuration and engineering deployment functions allow practitioners to quickly deploy models into productions. We have implemented some state-of-the-art projects, including person re-id, partial re-id, cross-domain re-id and vehicle re-id, and plan to release these pre-trained models on multiple benchmark datasets. FastReID is by far the most general and high-performance toolbox that supports single and multiple GPU servers, you can reproduce our project results very easily and are very welcome to use it, the code and models are available at https://github.com/JDAI-CV/fast-reid.

Mohan Zhou, Yalong Bai, Wei Zhang et al.

Most object recognition approaches predominantly focus on learning discriminative visual patterns while overlooking the holistic object structure. Though important, structure modeling usually requires significant manual annotations and therefore is labor-intensive. In this paper, we propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions into the traditional framework. We show the recognition backbone can be substantially enhanced for more robust representation learning, without any cost of extra annotation and inference speed. Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category. We then design a spatial context learning module for modeling the internal structures of the object, through predicting the relative positions within the extent. These two modules can be easily plugged into any backbone networks during training and detached at inference time. Extensive experiments show that our look-into-object approach (LIO) achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft). We also show that this learning paradigm is highly generalizable to other tasks such as object detection and segmentation (MS COCO). Project page: https://github.com/JDAI-CV/LIO.

Yingwei Pan, Ting Yao, Yehao Li et al.

Recent progress on fine-grained visual recognition and visual question answering has featured Bilinear Pooling, which effectively models the 2$^{nd}$ order interactions across multi-modal inputs. Nevertheless, there has not been evidence in support of building such interactions concurrently with attention mechanism for image captioning. In this paper, we introduce a unified attention block -- X-Linear attention block, that fully employs bilinear pooling to selectively capitalize on visual information or perform multi-modal reasoning. Technically, X-Linear attention block simultaneously exploits both the spatial and channel-wise bilinear attention distributions to capture the 2$^{nd}$ order interactions between the input single-modal or multi-modal features. Higher and even infinity order feature interactions are readily modeled through stacking multiple X-Linear attention blocks and equipping the block with Exponential Linear Unit (ELU) in a parameter-free fashion, respectively. Furthermore, we present X-Linear Attention Networks (dubbed as X-LAN) that novelly integrates X-Linear attention block(s) into image encoder and sentence decoder of image captioning model to leverage higher order intra- and inter-modal interactions. The experiments on COCO benchmark demonstrate that our X-LAN obtains to-date the best published CIDEr performance of 132.0% on COCO Karpathy test split. When further endowing Transformer with X-Linear attention blocks, CIDEr is boosted up to 132.8%. Source code is available at \url{https://github.com/Panda-Peter/image-captioning}.

Zhaofan Qiu, Ting Yao, Chong-Wah Ngo et al.

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for visual recognition problems. Nevertheless, the convolutional filters in these networks are local operations while ignoring the large-range dependency. Such drawback becomes even worse particularly for video recognition, since video is an information-intensive media with complex temporal variations. In this paper, we present a novel framework to boost the spatio-temporal representation learning by Local and Global Diffusion (LGD). Specifically, we construct a novel neural network architecture that learns the local and global representations in parallel. The architecture is composed of LGD blocks, where each block updates local and global features by modeling the diffusions between these two representations. Diffusions effectively interact two aspects of information, i.e., localized and holistic, for more powerful way of representation learning. Furthermore, a kernelized classifier is introduced to combine the representations from two aspects for video recognition. Our LGD networks achieve clear improvements on the large-scale Kinetics-400 and Kinetics-600 video classification datasets against the best competitors by 3.5% and 0.7%. We further examine the generalization of both the global and local representations produced by our pre-trained LGD networks on four different benchmarks for video action recognition and spatio-temporal action detection tasks. Superior performances over several state-of-the-art techniques on these benchmarks are reported. Code is available at: https://github.com/ZhaofanQiu/local-and-global-diffusion-networks.

Ting Yao, Yehao Li, Yingwei Pan et al.

The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input resolution of such hybrid backbones naturally strengthes model capacity, but inevitably suffers from heavy computational cost that scales quadratically. Instead, we present a new hybrid backbone with HIgh-Resolution Inputs (namely HIRI-ViT), that upgrades prevalent four-stage ViT to five-stage ViT tailored for high-resolution inputs. HIRI-ViT is built upon the seminal idea of decomposing the typical CNN operations into two parallel CNN branches in a cost-efficient manner. One high-resolution branch directly takes primary high-resolution features as inputs, but uses less convolution operations. The other low-resolution branch first performs down-sampling and then utilizes more convolution operations over such low-resolution features. Experiments on both recognition task (ImageNet-1K dataset) and dense prediction tasks (COCO and ADE20K datasets) demonstrate the superiority of HIRI-ViT. More remarkably, under comparable computational cost ($\sim$5.0 GFLOPs), HIRI-ViT achieves to-date the best published Top-1 accuracy of 84.3% on ImageNet with 448$\times$448 inputs, which absolutely improves 83.4% of iFormer-S by 0.9% with 224$\times$224 inputs.

Rui Zhu, Yingwei Pan, Yehao Li et al.

Diffusion Transformer (DiT) has emerged as the new trend of generative diffusion models on image generation. In view of extremely slow convergence in typical DiT, recent breakthroughs have been driven by mask strategy that significantly improves the training efficiency of DiT with additional intra-image contextual learning. Despite this progress, mask strategy still suffers from two inherent limitations: (a) training-inference discrepancy and (b) fuzzy relations between mask reconstruction & generative diffusion process, resulting in sub-optimal training of DiT. In this work, we address these limitations by novelly unleashing the self-supervised discrimination knowledge to boost DiT training. Technically, we frame our DiT in a teacher-student manner. The teacher-student discriminative pairs are built on the diffusion noises along the same Probability Flow Ordinary Differential Equation (PF-ODE). Instead of applying mask reconstruction loss over both DiT encoder and decoder, we decouple DiT encoder and decoder to separately tackle discriminative and generative objectives. In particular, by encoding discriminative pairs with student and teacher DiT encoders, a new discriminative loss is designed to encourage the inter-image alignment in the self-supervised embedding space. After that, student samples are fed into student DiT decoder to perform the typical generative diffusion task. Extensive experiments are conducted on ImageNet dataset, and our method achieves a competitive balance between training cost and generative capacity.

Qiao Jin, Xiaodong Chen, Wu Liu et al.

The advent of stereoscopic videos has opened new horizons in multimedia, particularly in extended reality (XR) and virtual reality (VR) applications, where immersive content captivates audiences across various platforms. Despite its growing popularity, producing stereoscopic videos remains challenging due to the technical complexities involved in generating stereo parallax. This refers to the positional differences of objects viewed from two distinct perspectives and is crucial for creating depth perception. This complex process poses significant challenges for creators aiming to deliver convincing and engaging presentations. To address these challenges, this paper introduces the Text-driven Stereoscopic Video Generation (T-SVG) system. This innovative, model-agnostic, zero-shot approach streamlines video generation by using text prompts to create reference videos. These videos are transformed into 3D point cloud sequences, which are rendered from two perspectives with subtle parallax differences, achieving a natural stereoscopic effect. T-SVG represents a significant advancement in stereoscopic content creation by integrating state-of-the-art, training-free techniques in text-to-video generation, depth estimation, and video inpainting. Its flexible architecture ensures high efficiency and user-friendliness, allowing seamless updates with newer models without retraining. By simplifying the production pipeline, T-SVG makes stereoscopic video generation accessible to a broader audience, demonstrating its potential to revolutionize the field.

Dong Li, Wenqi Zhong, Wei Yu et al.

Video virtual try-on aims to seamlessly dress a subject in a video with a specific garment. The primary challenge involves preserving the visual authenticity of the garment while dynamically adapting to the pose and physique of the subject. While existing methods have predominantly focused on image-based virtual try-on, extending these techniques directly to videos often results in temporal inconsistencies. Most current video virtual try-on approaches alleviate this challenge by incorporating temporal modules, yet still overlook the critical spatiotemporal pose interactions between human and garment. Effective pose interactions in videos should not only consider spatial alignment between human and garment poses in each frame but also account for the temporal dynamics of human poses throughout the entire video. With such motivation, we propose a new framework, namely Dynamic Pose Interaction Diffusion Models (DPIDM), to leverage diffusion models to delve into dynamic pose interactions for video virtual try-on. Technically, DPIDM introduces a skeleton-based pose adapter to integrate synchronized human and garment poses into the denoising network. A hierarchical attention module is then exquisitely designed to model intra-frame human-garment pose interactions and long-term human pose dynamics across frames through pose-aware spatial and temporal attention mechanisms. Moreover, DPIDM capitalizes on a temporal regularized attention loss between consecutive frames to enhance temporal consistency. Extensive experiments conducted on VITON-HD, VVT and ViViD datasets demonstrate the superiority of our DPIDM against the baseline methods. Notably, DPIDM achieves VFID score of 0.506 on VVT dataset, leading to 60.5% improvement over the state-of-the-art GPD-VVTO approach.

Jingtao Zhan, Qingyao Ai, Yiqun Liu et al.

For text-to-image generation, automatically refining user-provided natural language prompts into the keyword-enriched prompts favored by systems is essential for the user experience. Such a prompt refinement process is analogous to translating the prompt from "user languages" into "system languages". However, the scarcity of such parallel corpora makes it difficult to train a prompt refinement model. Inspired by zero-shot machine translation techniques, we introduce Prompt Refinement with Image Pivot (PRIP). PRIP innovatively uses the latent representation of a user-preferred image as an intermediary "pivot" between the user and system languages. It decomposes the refinement process into two data-rich tasks: inferring representations of user-preferred images from user languages and subsequently translating image representations into system languages. Thus, it can leverage abundant data for training. Extensive experiments show that PRIP substantially outperforms a wide range of baselines and effectively transfers to unseen systems in a zero-shot manner.

Dong Li, Zhaofan Qiu, Yingwei Pan et al.

Human actions are typically of combinatorial structures or patterns, i.e., subjects, objects, plus spatio-temporal interactions in between. Discovering such structures is therefore a rewarding way to reason about the dynamics of interactions and recognize the actions. In this paper, we introduce a new design of sub-graphs to represent and encode the discriminative patterns of each action in the videos. Specifically, we present MUlti-scale Sub-graph LEarning (MUSLE) framework that novelly builds space-time graphs and clusters the graphs into compact sub-graphs on each scale with respect to the number of nodes. Technically, MUSLE produces 3D bounding boxes, i.e., tubelets, in each video clip, as graph nodes and takes dense connectivity as graph edges between tubelets. For each action category, we execute online clustering to decompose the graph into sub-graphs on each scale through learning Gaussian Mixture Layer and select the discriminative sub-graphs as action prototypes for recognition. Extensive experiments are conducted on both Something-Something V1 & V2 and Kinetics-400 datasets, and superior results are reported when comparing to state-of-the-art methods. More remarkably, our MUSLE achieves to-date the best reported accuracy of 65.0% on Something-Something V2 validation set.

Yingwei Pan, Yue Chen, Qian Bao et al.

Live video broadcasting normally requires a multitude of skills and expertise with domain knowledge to enable multi-camera productions. As the number of cameras keep increasing, directing a live sports broadcast has now become more complicated and challenging than ever before. The broadcast directors need to be much more concentrated, responsive, and knowledgeable, during the production. To relieve the directors from their intensive efforts, we develop an innovative automated sports broadcast directing system, called Smart Director, which aims at mimicking the typical human-in-the-loop broadcasting process to automatically create near-professional broadcasting programs in real-time by using a set of advanced multi-view video analysis algorithms. Inspired by the so-called "three-event" construction of sports broadcast, we build our system with an event-driven pipeline consisting of three consecutive novel components: 1) the Multi-view Event Localization to detect events by modeling multi-view correlations, 2) the Multi-view Highlight Detection to rank camera views by the visual importance for view selection, 3) the Auto-Broadcasting Scheduler to control the production of broadcasting videos. To our best knowledge, our system is the first end-to-end automated directing system for multi-camera sports broadcasting, completely driven by the semantic understanding of sports events. It is also the first system to solve the novel problem of multi-view joint event detection by cross-view relation modeling. We conduct both objective and subjective evaluations on a real-world multi-camera soccer dataset, which demonstrate the quality of our auto-generated videos is comparable to that of the human-directed. Thanks to its faster response, our system is able to capture more fast-passing and short-duration events which are usually missed by human directors.

Zhaofan Qiu, Ting Yao, Chong-Wah Ngo et al.

Video content is multifaceted, consisting of objects, scenes, interactions or actions. The existing datasets mostly label only one of the facets for model training, resulting in the video representation that biases to only one facet depending on the training dataset. There is no study yet on how to learn a video representation from multifaceted labels, and whether multifaceted information is helpful for video representation learning. In this paper, we propose a new learning framework, MUlti-Faceted Integration (MUFI), to aggregate facets from different datasets for learning a representation that could reflect the full spectrum of video content. Technically, MUFI formulates the problem as visual-semantic embedding learning, which explicitly maps video representation into a rich semantic embedding space, and jointly optimizes video representation from two perspectives. One is to capitalize on the intra-facet supervision between each video and its own label descriptions, and the second predicts the "semantic representation" of each video from the facets of other datasets as the inter-facet supervision. Extensive experiments demonstrate that learning 3D CNN via our MUFI framework on a union of four large-scale video datasets plus two image datasets leads to superior capability of video representation. The pre-learnt 3D CNN with MUFI also shows clear improvements over other approaches on several downstream video applications. More remarkably, MUFI achieves 98.1%/80.9% on UCF101/HMDB51 for action recognition and 101.5% in terms of CIDEr-D score on MSVD for video captioning.

Zhaofan Qiu, Ting Yao, Yan Shu et al.

Video is complex due to large variations in motion and rich content in fine-grained visual details. Abstracting useful information from such information-intensive media requires exhaustive computing resources. This paper studies a two-step alternative that first condenses the video sequence to an informative "frame" and then exploits off-the-shelf image recognition system on the synthetic frame. A valid question is how to define "useful information" and then distill it from a video sequence down to one synthetic frame. This paper presents a novel Informative Frame Synthesis (IFS) architecture that incorporates three objective tasks, i.e., appearance reconstruction, video categorization, motion estimation, and two regularizers, i.e., adversarial learning, color consistency. Each task equips the synthetic frame with one ability, while each regularizer enhances its visual quality. With these, by jointly learning the frame synthesis in an end-to-end manner, the generated frame is expected to encapsulate the required spatio-temporal information useful for video analysis. Extensive experiments are conducted on the large-scale Kinetics dataset. When comparing to baseline methods that map video sequence to a single image, IFS shows superior performance. More remarkably, IFS consistently demonstrates evident improvements on image-based 2D networks and clip-based 3D networks, and achieves comparable performance with the state-of-the-art methods with less computational cost.

Yang Chen, Yu Wang, Yingwei Pan et al.

Mainstream state-of-the-art domain generalization algorithms tend to prioritize the assumption on semantic invariance across domains. Meanwhile, the inherent intra-domain style invariance is usually underappreciated and put on the shelf. In this paper, we reveal that leveraging intra-domain style invariance is also of pivotal importance in improving the efficiency of domain generalization. We verify that it is critical for the network to be informative on what domain features are invariant and shared among instances, so that the network sharpens its understanding and improves its semantic discriminative ability. Correspondingly, we also propose a novel "jury" mechanism, which is particularly effective in learning useful semantic feature commonalities among domains. Our complete model called STEAM can be interpreted as a novel probabilistic graphical model, for which the implementation requires convenient constructions of two kinds of memory banks: semantic feature bank and style feature bank. Empirical results show that our proposed framework surpasses the state-of-the-art methods by clear margins.

Yang Chen, Yingwei Pan, Yu Wang et al.

Self-supervised learning (SSL) has recently become the favorite among feature learning methodologies. It is therefore appealing for domain adaptation approaches to consider incorporating SSL. The intuition is to enforce instance-level feature consistency such that the predictor becomes somehow invariant across domains. However, most existing SSL methods in the regime of domain adaptation usually are treated as standalone auxiliary components, leaving the signatures of domain adaptation unattended. Actually, the optimal region where the domain gap vanishes and the instance level constraint that SSL peruses may not coincide at all. From this point, we present a particular paradigm of self-supervised learning tailored for domain adaptation, i.e., Transferrable Contrastive Learning (TCL), which links the SSL and the desired cross-domain transferability congruently. We find contrastive learning intrinsically a suitable candidate for domain adaptation, as its instance invariance assumption can be conveniently promoted to cross-domain class-level invariance favored by domain adaptation tasks. Based on particular memory bank constructions and pseudo label strategies, TCL then penalizes cross-domain intra-class domain discrepancy between source and target through a clean and novel contrastive loss. The free lunch is, thanks to the incorporation of contrastive learning, TCL relies on a moving-averaged key encoder that naturally achieves a temporally ensembled version of pseudo labels for target data, which avoids pseudo label error propagation at no extra cost. TCL therefore efficiently reduces cross-domain gaps. Through extensive experiments on benchmarks (Office-Home, VisDA-2017, Digits-five, PACS and DomainNet) for both single-source and multi-source domain adaptation tasks, TCL has demonstrated state-of-the-art performances.

Jianjie Luo, Yehao Li, Yingwei Pan et al.

BERT-type structure has led to the revolution of vision-language pre-training and the achievement of state-of-the-art results on numerous vision-language downstream tasks. Existing solutions dominantly capitalize on the multi-modal inputs with mask tokens to trigger mask-based proxy pre-training tasks (e.g., masked language modeling and masked object/frame prediction). In this work, we argue that such masked inputs would inevitably introduce noise for cross-modal matching proxy task, and thus leave the inherent vision-language association under-explored. As an alternative, we derive a particular form of cross-modal proxy objective for video-language pre-training, i.e., Contrastive Cross-modal matching and denoising (CoCo). By viewing the masked frame/word sequences as the noisy augmentation of primary unmasked ones, CoCo strengthens video-language association by simultaneously pursuing inter-modal matching and intra-modal denoising between masked and unmasked inputs in a contrastive manner. Our CoCo proxy objective can be further integrated into any BERT-type encoder-decoder structure for video-language pre-training, named as Contrastive Cross-modal BERT (CoCo-BERT). We pre-train CoCo-BERT on TV dataset and a newly collected large-scale GIF video dataset (ACTION). Through extensive experiments over a wide range of downstream tasks (e.g., cross-modal retrieval, video question answering, and video captioning), we demonstrate the superiority of CoCo-BERT as a pre-trained structure.