Yong Zhang

Yong Zhang, Yingwei Pan, Ting Yao et al.

Recent high-performing Human-Object Interaction (HOI) detection techniques have been highly influenced by Transformer-based object detector (i.e., DETR). Nevertheless, most of them directly map parametric interaction queries into a set of HOI predictions through vanilla Transformer in a one-stage manner. This leaves rich inter- or intra-interaction structure under-exploited. In this work, we design a novel Transformer-style HOI detector, i.e., Structure-aware Transformer over Interaction Proposals (STIP), for HOI detection. Such design decomposes the process of HOI set prediction into two subsequent phases, i.e., an interaction proposal generation is first performed, and then followed by transforming the non-parametric interaction proposals into HOI predictions via a structure-aware Transformer. The structure-aware Transformer upgrades vanilla Transformer by encoding additionally the holistically semantic structure among interaction proposals as well as the locally spatial structure of human/object within each interaction proposal, so as to strengthen HOI predictions. Extensive experiments conducted on V-COCO and HICO-DET benchmarks have demonstrated the effectiveness of STIP, and superior results are reported when comparing with the state-of-the-art HOI detectors. Source code is available at \url{https://github.com/zyong812/STIP}.

Kun Cheng, Xiaodong Cun, Yong Zhang et al. · tsinghua

We present VideoReTalking, a new system to edit the faces of a real-world talking head video according to input audio, producing a high-quality and lip-syncing output video even with a different emotion. Our system disentangles this objective into three sequential tasks: (1) face video generation with a canonical expression; (2) audio-driven lip-sync; and (3) face enhancement for improving photo-realism. Given a talking-head video, we first modify the expression of each frame according to the same expression template using the expression editing network, resulting in a video with the canonical expression. This video, together with the given audio, is then fed into the lip-sync network to generate a lip-syncing video. Finally, we improve the photo-realism of the synthesized faces through an identity-aware face enhancement network and post-processing. We use learning-based approaches for all three steps and all our modules can be tackled in a sequential pipeline without any user intervention. Furthermore, our system is a generic approach that does not need to be retrained to a specific person. Evaluations on two widely-used datasets and in-the-wild examples demonstrate the superiority of our framework over other state-of-the-art methods in terms of lip-sync accuracy and visual quality.

Mingdeng Cao, Yanbo Fan, Yong Zhang et al.

Video deblurring is still an unsolved problem due to the challenging spatio-temporal modeling process. While existing convolutional neural network-based methods show a limited capacity for effective spatial and temporal modeling for video deblurring. This paper presents VDTR, an effective Transformer-based model that makes the first attempt to adapt Transformer for video deblurring. VDTR exploits the superior long-range and relation modeling capabilities of Transformer for both spatial and temporal modeling. However, it is challenging to design an appropriate Transformer-based model for video deblurring due to the complicated non-uniform blurs, misalignment across multiple frames and the high computational costs for high-resolution spatial modeling. To address these problems, VDTR advocates performing attention within non-overlapping windows and exploiting the hierarchical structure for long-range dependencies modeling. For frame-level spatial modeling, we propose an encoder-decoder Transformer that utilizes multi-scale features for deblurring. For multi-frame temporal modeling, we adapt Transformer to fuse multiple spatial features efficiently. Compared with CNN-based methods, the proposed method achieves highly competitive results on both synthetic and real-world video deblurring benchmarks, including DVD, GOPRO, REDS and BSD. We hope such a Transformer-based architecture can serve as a powerful alternative baseline for video deblurring and other video restoration tasks. The source code will be available at \url{https://github.com/ljzycmd/VDTR}.

Yingqing He, Menghan Xia, Haoxin Chen et al. · tsinghua

Generating videos for visual storytelling can be a tedious and complex process that typically requires either live-action filming or graphics animation rendering. To bypass these challenges, our key idea is to utilize the abundance of existing video clips and synthesize a coherent storytelling video by customizing their appearances. We achieve this by developing a framework comprised of two functional modules: (i) Motion Structure Retrieval, which provides video candidates with desired scene or motion context described by query texts, and (ii) Structure-Guided Text-to-Video Synthesis, which generates plot-aligned videos under the guidance of motion structure and text prompts. For the first module, we leverage an off-the-shelf video retrieval system and extract video depths as motion structure. For the second module, we propose a controllable video generation model that offers flexible controls over structure and characters. The videos are synthesized by following the structural guidance and appearance instruction. To ensure visual consistency across clips, we propose an effective concept personalization approach, which allows the specification of the desired character identities through text prompts. Extensive experiments demonstrate that our approach exhibits significant advantages over various existing baselines.

Morgan Heisler, Amin Banitalebi-Dehkordi, Yong Zhang · tsinghua

Data augmentation is an essential technique in improving the generalization of deep neural networks. The majority of existing image-domain augmentations either rely on geometric and structural transformations, or apply different kinds of photometric distortions. In this paper, we propose an effective technique for image augmentation by injecting contextually meaningful knowledge into the scenes. Our method of semantically meaningful image augmentation for object detection via language grounding, SemAug, starts by calculating semantically appropriate new objects that can be placed into relevant locations in the image (the what and where problems). Then it embeds these objects into their relevant target locations, thereby promoting diversity of object instance distribution. Our method allows for introducing new object instances and categories that may not even exist in the training set. Furthermore, it does not require the additional overhead of training a context network, so it can be easily added to existing architectures. Our comprehensive set of evaluations showed that the proposed method is very effective in improving the generalization, while the overhead is negligible. In particular, for a wide range of model architectures, our method achieved ~2-4% and ~1-2% mAP improvements for the task of object detection on the Pascal VOC and COCO datasets, respectively.

Zhian Liu, Maomao Li, Yong Zhang et al.

We present a novel paradigm for high-fidelity face swapping that faithfully preserves the desired subtle geometry and texture details. We rethink face swapping from the perspective of fine-grained face editing, \textit{i.e., ``editing for swapping'' (E4S)}, and propose a framework that is based on the explicit disentanglement of the shape and texture of facial components. Following the E4S principle, our framework enables both global and local swapping of facial features, as well as controlling the amount of partial swapping specified by the user. Furthermore, the E4S paradigm is inherently capable of handling facial occlusions by means of facial masks. At the core of our system lies a novel Regional GAN Inversion (RGI) method, which allows the explicit disentanglement of shape and texture. It also allows face swapping to be performed in the latent space of StyleGAN. Specifically, we design a multi-scale mask-guided encoder to project the texture of each facial component into regional style codes. We also design a mask-guided injection module to manipulate the feature maps with the style codes. Based on the disentanglement, face swapping is reformulated as a simplified problem of style and mask swapping. Extensive experiments and comparisons with current state-of-the-art methods demonstrate the superiority of our approach in preserving texture and shape details, as well as working with high resolution images. The project page is http://e4s2022.github.io

Mohammad Akbari, Saeed Ranjbar Alvar, Behnam Kamranian et al.

Building multi-modal language models has been a trend in the recent years, where additional modalities such as image, video, speech, etc. are jointly learned along with natural languages (i.e., textual information). Despite the success of these multi-modal language models with different modalities, there is no existing solution for neural network architectures and natural languages. Providing neural architectural information as a new modality allows us to provide fast architecture-2-text and text-2-architecture retrieval/generation services on the cloud with a single inference. Such solution is valuable in terms of helping beginner and intermediate ML users to come up with better neural architectures or AutoML approaches with a simple text query. In this paper, we propose ArchBERT, a bi-modal model for joint learning and understanding of neural architectures and natural languages, which opens up new avenues for research in this area. We also introduce a pre-training strategy named Masked Architecture Modeling (MAM) for a more generalized joint learning. Moreover, we introduce and publicly release two new bi-modal datasets for training and validating our methods. The ArchBERT's performance is verified through a set of numerical experiments on different downstream tasks such as architecture-oriented reasoning, question answering, and captioning (summarization). Datasets, codes, and demos are available supplementary materials.

Ming Li, Yong Zhang, Shwai He et al.

Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But it also leads to extra cost and computation due to the involvement of LLMs in this process. To reduce the filtering cost, we study Superfiltering: Can we use a smaller and weaker model to select data for finetuning a larger and stronger model? Despite the performance gap between weak and strong language models, we find their highly consistent capability to perceive instruction difficulty and data selection results. This enables us to use a much smaller and more efficient model to filter the instruction data used to train a larger language model. Not only does it largely speed up the data filtering, but the filtered-data-finetuned LLM achieves even better performance on standard benchmarks. Extensive experiments validate the efficacy and efficiency of our approach.

Yuanen Zhou, Yong Zhang, Zhenzhen Hu et al.

Current state-of-the-art image captioning models adopt autoregressive decoders, \ie they generate each word by conditioning on previously generated words, which leads to heavy latency during inference. To tackle this issue, non-autoregressive image captioning models have recently been proposed to significantly accelerate the speed of inference by generating all words in parallel. However, these non-autoregressive models inevitably suffer from large generation quality degradation since they remove words dependence excessively. To make a better trade-off between speed and quality, we introduce a semi-autoregressive model for image captioning~(dubbed as SATIC), which keeps the autoregressive property in global but generates words parallelly in local . Based on Transformer, there are only a few modifications needed to implement SATIC. Experimental results on the MSCOCO image captioning benchmark show that SATIC can achieve a good trade-off without bells and whistles. Code is available at {\color{magenta}\url{https://github.com/YuanEZhou/satic}}.

Shulan Ruan, Yong Zhang, Kun Zhang et al.

Text-to-image synthesis refers to generating an image from a given text description, the key goal of which lies in photo realism and semantic consistency. Previous methods usually generate an initial image with sentence embedding and then refine it with fine-grained word embedding. Despite the significant progress, the 'aspect' information (e.g., red eyes) contained in the text, referring to several words rather than a word that depicts 'a particular part or feature of something', is often ignored, which is highly helpful for synthesizing image details. How to make better utilization of aspect information in text-to-image synthesis still remains an unresolved challenge. To address this problem, in this paper, we propose a Dynamic Aspect-awarE GAN (DAE-GAN) that represents text information comprehensively from multiple granularities, including sentence-level, word-level, and aspect-level. Moreover, inspired by human learning behaviors, we develop a novel Aspect-aware Dynamic Re-drawer (ADR) for image refinement, in which an Attended Global Refinement (AGR) module and an Aspect-aware Local Refinement (ALR) module are alternately employed. AGR utilizes word-level embedding to globally enhance the previously generated image, while ALR dynamically employs aspect-level embedding to refine image details from a local perspective. Finally, a corresponding matching loss function is designed to ensure the text-image semantic consistency at different levels. Extensive experiments on two well-studied and publicly available datasets (i.e., CUB-200 and COCO) demonstrate the superiority and rationality of our method.

Gengcong Yang, Jingyi Zhang, Yong Zhang et al.

To generate "accurate" scene graphs, almost all existing methods predict pairwise relationships in a deterministic manner. However, we argue that visual relationships are often semantically ambiguous. Specifically, inspired by linguistic knowledge, we classify the ambiguity into three types: Synonymy Ambiguity, Hyponymy Ambiguity, and Multi-view Ambiguity. The ambiguity naturally leads to the issue of \emph{implicit multi-label}, motivating the need for diverse predictions. In this work, we propose a novel plug-and-play Probabilistic Uncertainty Modeling (PUM) module. It models each union region as a Gaussian distribution, whose variance measures the uncertainty of the corresponding visual content. Compared to the conventional deterministic methods, such uncertainty modeling brings stochasticity of feature representation, which naturally enables diverse predictions. As a byproduct, PUM also manages to cover more fine-grained relationships and thus alleviates the issue of bias towards frequent relationships. Extensive experiments on the large-scale Visual Genome benchmark show that combining PUM with newly proposed ResCAGCN can achieve state-of-the-art performances, especially under the mean recall metric. Furthermore, we prove the universal effectiveness of PUM by plugging it into some existing models and provide insightful analysis of its ability to generate diverse yet plausible visual relationships.

Jingyi Zhang, Yong Zhang, Baoyuan Wu et al.

Visual scene graph generation is a challenging task. Previous works have achieved great progress, but most of them do not explicitly consider the class imbalance issue in scene graph generation. Models learned without considering the class imbalance tend to predict the majority classes, which leads to a good performance on trivial frequent predicates, but poor performance on informative infrequent predicates. However, predicates of minority classes often carry more semantic and precise information~(\textit{e.g.}, \emph{`on'} v.s \emph{`parked on'}). % which leads to a good score of recall, but a poor score of mean recall. To alleviate the influence of the class imbalance, we propose a novel model, dubbed \textit{dual ResGCN}, which consists of an object residual graph convolutional network and a relation residual graph convolutional network. The two networks are complementary to each other. The former captures object-level context information, \textit{i.e.,} the connections among objects. We propose a novel ResGCN that enhances object features in a cross attention manner. Besides, we stack multiple contextual coefficients to alleviate the imbalance issue and enrich the prediction diversity. The latter is carefully designed to explicitly capture relation-level context information \textit{i.e.,} the connections among relations. We propose to incorporate the prior about the co-occurrence of relation pairs into the graph to further help alleviate the class imbalance issue. Extensive evaluations of three tasks are performed on the large-scale database VG to demonstrate the superiority of the proposed method.