Chen Zhao

Kristen Grauman, Andrew Westbury, Lorenzo Torresani et al. · cmu, gatech

We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions -- including a novel "expert commentary" done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community. Project page: http://ego-exo4d-data.org/

Chong Mou, Youmin Xu, Jiechong Song et al.

Video steganography is the art of unobtrusively concealing secret data in a cover video and then recovering the secret data through a decoding protocol at the receiver end. Although several attempts have been made, most of them are limited to low-capacity and fixed steganography. To rectify these weaknesses, we propose a Large-capacity and Flexible Video Steganography Network (LF-VSN) in this paper. For large-capacity, we present a reversible pipeline to perform multiple videos hiding and recovering through a single invertible neural network (INN). Our method can hide/recover 7 secret videos in/from 1 cover video with promising performance. For flexibility, we propose a key-controllable scheme, enabling different receivers to recover particular secret videos from the same cover video through specific keys. Moreover, we further improve the flexibility by proposing a scalable strategy in multiple videos hiding, which can hide variable numbers of secret videos in a cover video with a single model and a single training session. Extensive experiments demonstrate that with the significant improvement of the video steganography performance, our proposed LF-VSN has high security, large hiding capacity, and flexibility. The source code is available at https://github.com/MC-E/LF-VSN.

Juan Leon Alcazar, Moritz Cordes, Chen Zhao et al.

Recent advances in the Active Speaker Detection (ASD) problem build upon a two-stage process: feature extraction and spatio-temporal context aggregation. In this paper, we propose an end-to-end ASD workflow where feature learning and contextual predictions are jointly learned. Our end-to-end trainable network simultaneously learns multi-modal embeddings and aggregates spatio-temporal context. This results in more suitable feature representations and improved performance in the ASD task. We also introduce interleaved graph neural network (iGNN) blocks, which split the message passing according to the main sources of context in the ASD problem. Experiments show that the aggregated features from the iGNN blocks are more suitable for ASD, resulting in state-of-the art performance. Finally, we design a weakly-supervised strategy, which demonstrates that the ASD problem can also be approached by utilizing audiovisual data but relying exclusively on audio annotations. We achieve this by modelling the direct relationship between the audio signal and the possible sound sources (speakers), as well as introducing a contrastive loss. All the resources of this project will be made available at: https://github.com/fuankarion/end-to-end-asd.

Guocheng Qian, Xuanyang Zhang, Guohao Li et al.

The key challenge in neural architecture search (NAS) is designing how to explore wisely in the huge search space. We propose a new NAS method called TNAS (NAS with trees), which improves search efficiency by exploring only a small number of architectures while also achieving a higher search accuracy. TNAS introduces an architecture tree and a binary operation tree, to factorize the search space and substantially reduce the exploration size. TNAS performs a modified bi-level Breadth-First Search in the proposed trees to discover a high-performance architecture. Impressively, TNAS finds the global optimal architecture on CIFAR-10 with test accuracy of 94.37\% in four GPU hours in NAS-Bench-201. The average test accuracy is 94.35\%, which outperforms the state-of-the-art. Code is available at: \url{https://github.com/guochengqian/TNAS}.

Shuming Liu, Chen-Lin Zhang, Chen Zhao et al.

Recently, temporal action detection (TAD) has seen significant performance improvement with end-to-end training. However, due to the memory bottleneck, only models with limited scales and limited data volumes can afford end-to-end training, which inevitably restricts TAD performance. In this paper, we reduce the memory consumption for end-to-end training, and manage to scale up the TAD backbone to 1 billion parameters and the input video to 1,536 frames, leading to significant detection performance. The key to our approach lies in our proposed temporal-informative adapter (TIA), which is a novel lightweight module that reduces training memory. Using TIA, we free the humongous backbone from learning to adapt to the TAD task by only updating the parameters in TIA. TIA also leads to better TAD representation by temporally aggregating context from adjacent frames throughout the backbone. We evaluate our model across four representative datasets. Owing to our efficient design, we are able to train end-to-end on VideoMAEv2-giant and achieve 75.4% mAP on THUMOS14, being the first end-to-end model to outperform the best feature-based methods. Code is available at https://github.com/sming256/AdaTAD.

Chen Zhao, Shuming Liu, Karttikeya Mangalam et al.

Temporal action localization (TAL) requires long-form reasoning to predict actions of various durations and complex content. Given limited GPU memory, training TAL end to end (i.e., from videos to predictions) on long videos is a significant challenge. Most methods can only train on pre-extracted features without optimizing them for the localization problem, consequently limiting localization performance. In this work, to extend the potential in TAL networks, we propose a novel end-to-end method Re2TAL, which rewires pretrained video backbones for reversible TAL. Re2TAL builds a backbone with reversible modules, where the input can be recovered from the output such that the bulky intermediate activations can be cleared from memory during training. Instead of designing one single type of reversible module, we propose a network rewiring mechanism, to transform any module with a residual connection to a reversible module without changing any parameters. This provides two benefits: (1) a large variety of reversible networks are easily obtained from existing and even future model designs, and (2) the reversible models require much less training effort as they reuse the pre-trained parameters of their original non-reversible versions. Re2TAL, only using the RGB modality, reaches 37.01% average mAP on ActivityNet-v1.3, a new state-of-the-art record, and mAP 64.9% at tIoU=0.5 on THUMOS-14, outperforming all other RGB-only methods.

Chen Zhao, Dawei Du, Anthony Hoogs et al.

Existing methods for open-set action recognition focus on novelty detection that assumes video clips show a single action, which is unrealistic in the real world. We propose a new method for open set action recognition and novelty detection via MUlti-Label Evidential learning (MULE), that goes beyond previous novel action detection methods by addressing the more general problems of single or multiple actors in the same scene, with simultaneous action(s) by any actor. Our Beta Evidential Neural Network estimates multi-action uncertainty with Beta densities based on actor-context-object relation representations. An evidence debiasing constraint is added to the objective function for optimization to reduce the static bias of video representations, which can incorrectly correlate predictions and static cues. We develop a learning algorithm based on a primal-dual average scheme update to optimize the proposed problem. Theoretical analysis of the optimization algorithm demonstrates the convergence of the primal solution sequence and bounds for both the loss function and the debiasing constraint. Uncertainty and belief-based novelty estimation mechanisms are formulated to detect novel actions. Extensive experiments on two real-world video datasets show that our proposed approach achieves promising performance in single/multi-actor, single/multi-action settings.

Chen Zhao, Yinlin Hu, Mathieu Salzmann

In this paper, we tackle the task of estimating the 3D orientation of previously-unseen objects from monocular images. This task contrasts with the one considered by most existing deep learning methods which typically assume that the testing objects have been observed during training. To handle the unseen objects, we follow a retrieval-based strategy and prevent the network from learning object-specific features by computing multi-scale local similarities between the query image and synthetically-generated reference images. We then introduce an adaptive fusion module that robustly aggregates the local similarities into a global similarity score of pairwise images. Furthermore, we speed up the retrieval process by developing a fast retrieval strategy. Our experiments on the LineMOD, LineMOD-Occluded, and T-LESS datasets show that our method yields a significantly better generalization to unseen objects than previous works. Our code and pre-trained models are available at https://sailor-z.github.io/projects/Unseen_Object_Pose.html.

Jinbo Wu, Xiaobo Gao, Xing Liu et al.

In this paper, we study Text-to-3D content generation leveraging 2D diffusion priors to enhance the quality and detail of the generated 3D models. Recent progress (Magic3D) in text-to-3D has shown that employing high-resolution (e.g., 512 x 512) renderings can lead to the production of high-quality 3D models using latent diffusion priors. To enable rendering at even higher resolutions, which has the potential to further augment the quality and detail of the models, we propose a novel approach that combines multiple noise estimation processes with a pretrained 2D diffusion prior. Distinct from the Bar-Tal et al.s' study which binds multiple denoised results to generate images from texts, our approach integrates the computation of scoring distillation losses such as SDS loss and VSD loss which are essential techniques for the 3D content generation with 2D diffusion priors. We experimentally evaluated the proposed approach. The results show that the proposed approach can generate high-quality details compared to the baselines.

Shuming Liu, Mengmeng Xu, Chen Zhao et al.

Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an efficient temporal action detector (ETAD) that can train directly from video frames with extremely low GPU memory consumption. Our main idea is to minimize and balance the heavy computation among features and gradients in each training iteration. We propose to sequentially forward the snippet frame through the video encoder, and backward only a small necessary portion of gradients to update the encoder. To further alleviate the computational redundancy in training, we propose to dynamically sample only a small subset of proposals during training. Moreover, various sampling strategies and ratios are studied for both the encoder and detector. ETAD achieves state-of-the-art performance on TAD benchmarks with remarkable efficiency. On ActivityNet-1.3, training ETAD in 18 hours can reach 38.25% average mAP with only 1.3 GB memory consumption per video under end-to-end training. Our code will be publicly released.

Shuming Liu, Lin Sui, Chen-Lin Zhang et al.

As a fundamental task in long-form video understanding, temporal action detection (TAD) aims to capture inherent temporal relations in untrimmed videos and identify candidate actions with precise boundaries. Over the years, various networks, including convolutions, graphs, and transformers, have been explored for effective temporal modeling for TAD. However, these modules typically treat past and future information equally, overlooking the crucial fact that changes in action boundaries are essentially causal events. Inspired by this insight, we propose leveraging the temporal causality of actions to enhance TAD representation by restricting the model's access to only past or future context. We introduce CausalTAD, which combines causal attention and causal Mamba to achieve state-of-the-art performance on multiple benchmarks. Notably, with CausalTAD, we ranked 1st in the Action Recognition, Action Detection, and Audio-Based Interaction Detection tracks at the EPIC-Kitchens Challenge 2024, as well as 1st in the Moment Queries track at the Ego4D Challenge 2024. Our code is available at https://github.com/sming256/OpenTAD/.

Chen Zhao, Yinlin Hu, Mathieu Salzmann

Object location prior is critical for the standard 6D object pose estimation setting. The prior can be used to initialize the 3D object translation and facilitate 3D object rotation estimation. Unfortunately, the object detectors that are used for this purpose do not generalize to unseen objects. Therefore, existing 6D pose estimation methods for unseen objects either assume the ground-truth object location to be known or yield inaccurate results when it is unavailable. In this paper, we address this problem by developing a method, LocPoseNet, able to robustly learn location prior for unseen objects. Our method builds upon a template matching strategy, where we propose to distribute the reference kernels and convolve them with a query to efficiently compute multi-scale correlations. We then introduce a novel translation estimator, which decouples scale-aware and scale-robust features to predict different object location parameters. Our method outperforms existing works by a large margin on LINEMOD and GenMOP. We further construct a challenging synthetic dataset, which allows us to highlight the better robustness of our method to various noise sources. Our project website is at: https://sailor-z.github.io/projects/3DV2024_LocPoseNet.html.

Chen Zhao, Merey Ramazanova, Mengmeng Xu et al.

Temporal action detection (TAD) is an important yet challenging task in video analysis. Most existing works draw inspiration from image object detection and tend to reformulate it as a proposal generation - classification problem. However, there are two caveats with this paradigm. First, proposals are not equipped with annotated labels, which have to be empirically compiled, thus the information in the annotations is not necessarily precisely employed in the model training process. Second, there are large variations in the temporal scale of actions, and neglecting this fact may lead to deficient representation in the video features. To address these issues and precisely model temporal action detection, we formulate the task of temporal action detection in a novel perspective of semantic segmentation. Owing to the 1-dimensional property of TAD, we are able to convert the coarse-grained detection annotations to fine-grained semantic segmentation annotations for free. We take advantage of them to provide precise supervision so as to mitigate the impact induced by the imprecise proposal labels. We propose an end-to-end framework SegTAD composed of a 1D semantic segmentation network (1D-SSN) and a proposal detection network (PDN).

Feng Mi, Chen Zhao, Zhuoyi Wang et al.

With the increase of the adoption of blockchain technology in providing decentralized solutions to various problems, smart contracts have become more popular to the point that billions of US Dollars are currently exchanged every day through such technology. Meanwhile, various vulnerabilities in smart contracts have been exploited by attackers to steal cryptocurrencies worth millions of dollars. The automatic detection of smart contract vulnerabilities therefore is an essential research problem. Existing solutions to this problem particularly rely on human experts to define features or different rules to detect vulnerabilities. However, this often causes many vulnerabilities to be ignored, and they are inefficient in detecting new vulnerabilities. In this study, to overcome such challenges, we propose a framework to automatically detect vulnerabilities in smart contracts on the blockchain. More specifically, first, we utilize novel feature vector generation techniques from bytecode of smart contract since the source code of smart contracts are rarely available in public. Next, the collected vectors are fed into our novel metric learning-based deep neural network(DNN) to get the detection result. We conduct comprehensive experiments on large-scale benchmarks, and the quantitative results demonstrate the effectiveness and efficiency of our approach.

Hongge Chen, Zhao Chen, Gregory P. Meyer et al.

We present SHIFT3D, a differentiable pipeline for generating 3D shapes that are structurally plausible yet challenging to 3D object detectors. In safety-critical applications like autonomous driving, discovering such novel challenging objects can offer insight into unknown vulnerabilities of 3D detectors. By representing objects with a signed distanced function (SDF), we show that gradient error signals allow us to smoothly deform the shape or pose of a 3D object in order to confuse a downstream 3D detector. Importantly, the objects generated by SHIFT3D physically differ from the baseline object yet retain a semantically recognizable shape. Our approach provides interpretable failure modes for modern 3D object detectors, and can aid in preemptive discovery of potential safety risks within 3D perception systems before these risks become critical failures.

Chen Zhao, Wei-Ling Cai, Zheng Yuan et al.

Recently, unsupervised image-to-image translation methods based on contrastive learning have achieved state-of-the-art results in many tasks. However, in the previous works, the negatives are sampled from the input image itself, which inspires us to design a data augmentation method to improve the quality of the selected negatives. Moreover, the previous methods only preserve the content consistency via patch-wise contrastive learning in the embedding space, which ignores the domain consistency between the generated images and the real images of the target domain. In this paper, we propose a novel unsupervised image-to-image translation framework based on multi-cropping contrastive learning and domain consistency, called MCDUT. Specifically, we obtain the multi-cropping views via the center-cropping and the random-cropping with the aim of further generating the high-quality negative examples. To constrain the embeddings in the deep feature space, we formulate a new domain consistency loss, which encourages the generated images to be close to the real images in the embedding space of the same domain. Furthermore, we present a dual coordinate attention network by embedding positional information into the channel, which called DCA. We employ the DCA network in the design of generator, which makes the generator capture the horizontal and vertical global information of dependency. In many image-to-image translation tasks, our method achieves state-of-the-art results, and the advantages of our method have been proven through extensive comparison experiments and ablation research.

Vaibhav Mavi, Abulhair Saparov, Chen Zhao

Applying existing question answering (QA) systems to specialized domains like law and finance presents challenges that necessitate domain expertise. Although large language models (LLMs) have shown impressive language comprehension and in-context learning capabilities, their inability to handle very long inputs/contexts is well known. Tasks specific to these domains need significant background knowledge, leading to contexts that can often exceed the maximum length that existing LLMs can process. This study explores leveraging the semi-structured nature of legal and financial data to efficiently retrieve relevant context, enabling the use of LLMs for domain-specialized QA. The resulting system outperforms contemporary models and also provides useful explanations for the answers, encouraging the integration of LLMs into legal and financial NLP systems for future research.

Yahao Shi, Yanmin Wu, Chenming Wu et al. · pku

This paper presents a 3D Gaussian Inverse Rendering (GIR) method, employing 3D Gaussian representations to effectively factorize the scene into material properties, light, and geometry. The key contributions lie in three-fold. We compute the normal of each 3D Gaussian using the shortest eigenvector, with a directional masking scheme forcing accurate normal estimation without external supervision. We adopt an efficient voxel-based indirect illumination tracing scheme that stores direction-aware outgoing radiance in each 3D Gaussian to disentangle secondary illumination for approximating multi-bounce light transport. To further enhance the illumination disentanglement, we represent a high-resolution environmental map with a learnable low-resolution map and a lightweight, fully convolutional network. Our method achieves state-of-the-art performance in both relighting and novel view synthesis tasks among the recently proposed inverse rendering methods while achieving real-time rendering. This substantiates our proposed method's efficacy and broad applicability, highlighting its potential as an influential tool in various real-time interactive graphics applications such as material editing and relighting. The code will be released at https://github.com/guduxiaolang/GIR.

Haozhe Qi, Chen Zhao, Mathieu Salzmann et al.

Human hands are highly articulated and versatile at handling objects. Jointly estimating the 3D poses of a hand and the object it manipulates from a monocular camera is challenging due to frequent occlusions. Thus, existing methods often rely on intermediate 3D shape representations to increase performance. These representations are typically explicit, such as 3D point clouds or meshes, and thus provide information in the direct surroundings of the intermediate hand pose estimate. To address this, we introduce HOISDF, a Signed Distance Field (SDF) guided hand-object pose estimation network, which jointly exploits hand and object SDFs to provide a global, implicit representation over the complete reconstruction volume. Specifically, the role of the SDFs is threefold: equip the visual encoder with implicit shape information, help to encode hand-object interactions, and guide the hand and object pose regression via SDF-based sampling and by augmenting the feature representations. We show that HOISDF achieves state-of-the-art results on hand-object pose estimation benchmarks (DexYCB and HO3Dv2). Code is available at https://github.com/amathislab/HOISDF

Chen Zhao, Tong Zhang, Mathieu Salzmann

Prior methods that tackle the problem of generalizable object pose estimation highly rely on having dense views of the unseen object. By contrast, we address the scenario where only a single reference view of the object is available. Our goal then is to estimate the relative object pose between this reference view and a query image that depicts the object in a different pose. In this scenario, robust generalization is imperative due to the presence of unseen objects during testing and the large-scale object pose variation between the reference and the query. To this end, we present a new hypothesis-and-verification framework, in which we generate and evaluate multiple pose hypotheses, ultimately selecting the most reliable one as the relative object pose. To measure reliability, we introduce a 3D-aware verification that explicitly applies 3D transformations to the 3D object representations learned from the two input images. Our comprehensive experiments on the Objaverse, LINEMOD, and CO3D datasets evidence the superior accuracy of our approach in relative pose estimation and its robustness in large-scale pose variations, when dealing with unseen objects.

Jiaofen Nan, Gaodeng Fan, Kaifan Zhang et al.

In the field of medical image analysis, image registration is a crucial technique. Despite the numerous registration models that have been proposed, existing methods still fall short in terms of accuracy and interpretability. In this paper, we present MsMorph, a deep learning-based image registration framework aimed at mimicking the manual process of registering image pairs to achieve more similar deformations, where the registered image pairs exhibit consistency or similarity in features. By extracting the feature differences between image pairs across various as-pects using gradients, the framework decodes semantic information at different scales and continuously compen-sates for the predicted deformation field, driving the optimization of parameters to significantly improve registration accuracy. The proposed method simulates the manual approach to registration, focusing on different regions of the image pairs and their neighborhoods to predict the deformation field between the two images, which provides strong interpretability. We compared several existing registration methods on two public brain MRI datasets, including LPBA and Mindboggle. The experimental results show that our method consistently outperforms state of the art in terms of metrics such as Dice score, Hausdorff distance, average symmetric surface distance, and non-Jacobian. The source code is publicly available at https://github.com/GaodengFan/MsMorph

Mattia Soldan, Alejandro Pardo, Juan León Alcázar et al.

The recent and increasing interest in video-language research has driven the development of large-scale datasets that enable data-intensive machine learning techniques. In comparison, limited effort has been made at assessing the fitness of these datasets for the video-language grounding task. Recent works have begun to discover significant limitations in these datasets, suggesting that state-of-the-art techniques commonly overfit to hidden dataset biases. In this work, we present MAD (Movie Audio Descriptions), a novel benchmark that departs from the paradigm of augmenting existing video datasets with text annotations and focuses on crawling and aligning available audio descriptions of mainstream movies. MAD contains over 384,000 natural language sentences grounded in over 1,200 hours of videos and exhibits a significant reduction in the currently diagnosed biases for video-language grounding datasets. MAD's collection strategy enables a novel and more challenging version of video-language grounding, where short temporal moments (typically seconds long) must be accurately grounded in diverse long-form videos that can last up to three hours. We have released MAD's data and baselines code at https://github.com/Soldelli/MAD.

Chen Zhao, Shuming Liu, Karttikeya Mangalam et al.

Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks by end-to-end finetuning, which is highly memory-intensive for tasks with high-resolution data, e.g., video understanding, small object detection, and point cloud analysis. In this paper, we propose Dynamic Reversible Dual-Residual Networks, or Dr$^2$Net, a novel family of network architectures that acts as a surrogate network to finetune a pretrained model with substantially reduced memory consumption. Dr$^2$Net contains two types of residual connections, one maintaining the residual structure in the pretrained models, and the other making the network reversible. Due to its reversibility, intermediate activations, which can be reconstructed from output, are cleared from memory during training. We use two coefficients on either type of residual connections respectively, and introduce a dynamic training strategy that seamlessly transitions the pretrained model to a reversible network with much higher numerical precision. We evaluate Dr$^2$Net on various pretrained models and various tasks, and show that it can reach comparable performance to conventional finetuning but with significantly less memory usage.

Jinzhi Zheng, Libo Zhang, Yanjun Wu et al.

Segmentation-based scene text detection algorithms can handle arbitrary shape scene texts and have strong robustness and adaptability, so it has attracted wide attention. Existing segmentation-based scene text detection algorithms usually only segment the pixels in the center region of the text, while ignoring other information of the text region, such as edge information, distance information, etc., thus limiting the detection accuracy of the algorithm for scene text. This paper proposes a plug-and-play module called the Region Multiple Information Perception Module (RMIPM) to enhance the detection performance of segmentation-based algorithms. Specifically, we design an improved module that can perceive various types of information about scene text regions, such as text foreground classification maps, distance maps, direction maps, etc. Experiments on MSRA-TD500 and TotalText datasets show that our method achieves comparable performance with current state-of-the-art algorithms.

Angelica Chen, Jason Phang, Alicia Parrish et al.

Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but this success is typically evaluated via correctness rather than consistency. We argue that self-consistency is an important criteria for valid multi-step reasoning in tasks where the solution is composed of the answers to multiple sub-steps. We propose two types of self-consistency that are particularly important for multi-step reasoning -- hypothetical consistency (a model's ability to predict what its output would be in a hypothetical other context) and compositional consistency (consistency of a model's final outputs when intermediate sub-steps are replaced with the model's outputs for those steps). We demonstrate that multiple variants of the GPT-3/-4 models exhibit poor consistency rates across both types of consistency on a variety of tasks.

Merey Ramazanova, Victor Escorcia, Fabian Caba Heilbron et al.

Egocentric videos capture sequences of human activities from a first-person perspective and can provide rich multimodal signals. However, most current localization methods use third-person videos and only incorporate visual information. In this work, we take a deep look into the effectiveness of audiovisual context in detecting actions in egocentric videos and introduce a simple-yet-effective approach via Observing, Watching, and Listening (OWL). OWL leverages audiovisual information and context for egocentric temporal action localization (TAL). We validate our approach in two large-scale datasets, EPIC-Kitchens, and HOMAGE. Extensive experiments demonstrate the relevance of the audiovisual temporal context. Namely, we boost the localization performance (mAP) over visual-only models by +2.23% and +3.35% in the above datasets.

Kristen Grauman, Andrew Westbury, Eugene Byrne et al.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

Chen Zhao, Yixiao Ge, Feng Zhu et al.

Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences. The selection is challenging since putative matches are typically extremely unbalanced, largely dominated by outliers, and the random distribution of such outliers further complicates the learning process for learning-based methods. To address this issue, we propose to progressively prune the correspondences via a local-to-global consensus learning procedure. We introduce a ``pruning'' block that lets us identify reliable candidates among the initial matches according to consensus scores estimated using local-to-global dynamic graphs. We then achieve progressive pruning by stacking multiple pruning blocks sequentially. Our method outperforms state-of-the-arts on robust line fitting, camera pose estimation and retrieval-based image localization benchmarks by significant margins and shows promising generalization ability to different datasets and detector/descriptor combinations.

Yao Lu, Sören Pirk, Jan Dlabal et al.

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e.g. object classification, detection, scene segmentation, depth estimation, etc. We show that we can leverage the inherent relationships among collections of tasks, as they are trained jointly, supervising each other through their known relationships via consistency losses. Furthermore, explicitly utilizing the relationships between tasks allows improving their performance while dramatically reducing the need for labeled data, and allows training with additional unsupervised or simulated data. We demonstrate a distributed joint training algorithm with task-level parallelism, which affords a high degree of asynchronicity and robustness. This allows learning across multiple tasks, or with large amounts of input data, at scale. We demonstrate our framework on subsets of the following collection of tasks: depth and normal prediction, semantic segmentation, 3D motion and ego-motion estimation, and object tracking and 3D detection in point clouds. We observe improved performance across these tasks, especially in the low-label regime.

Chen Zhao, Jiaqi Yang, Xin Xiong et al.

Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have conducted experiments on synthetic datasets with well-aligned data; while real-world point clouds are often not pre-aligned. How to achieve rotation invariance remains an open problem in point cloud analysis. To meet this challenge, we propose a novel approach toward achieving rotation-invariant (RI) representations by combining local geometry with global topology. In our local-global-representation (LGR)-Net, we have designed a two-branch network where one stream encodes local geometric RI features and the other encodes global topology-preserving RI features. Motivated by the observation that local geometry and global topology have different yet complementary RI responses in varying regions, two-branch RI features are fused by an innovative multi-layer perceptron (MLP) based attention module. To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis. Extensive experiments have demonstrated that our LGR-Net achieves the state-of-the-art performance on various rotation-augmented versions of ModelNet40, ShapeNet, ScanObjectNN, and S3DIS.

Chen Zhao, Jiaqi Yang, Ke Xian et al.

Matching corresponding features between two images is a fundamental task to computer vision with numerous applications in object recognition, robotics, and 3D reconstruction. Current state of the art in image feature matching has focused on establishing a single consistency in static scenes; by contrast, finding multiple consistencies in dynamic scenes has been under-researched. In this paper, we present an end-to-end optimization framework named "iterative clustering with Game-Theoretic Matching" (ic-GTM) for robust multi-consistency correspondence. The key idea is to formulate multi-consistency matching as a generalized clustering problem for an image pair. In our formulation, several local matching games are simultaneously carried out in different corresponding block pairs under the guidance of a novel payoff function consisting of both geometric and descriptive compatibility; the global matching results are further iteratively refined by clustering and thresholding with respect to a payoff matrix. We also propose three new metrics for evaluating the performance of multi-consistency image feature matching. Extensive experimental results have shown that the proposed framework significantly outperforms previous state-of-the-art approaches on both singleconsistency and multi-consistency datasets.

Chen Zhao, Jiaqi Yang, Yang Xiao et al.

Correspondence selection aiming at seeking correct feature correspondences from raw feature matches is pivotal for a number of feature-matching-based tasks. Various 2D (image) correspondence selection algorithms have been presented with decades of progress. Unfortunately, the lack of an in-depth evaluation makes it difficult for developers to choose a proper algorithm given a specific application. This paper fills this gap by evaluating eight 2D correspondence selection algorithms ranging from classical methods to the most recent ones on four standard datasets. The diversity of experimental datasets brings various nuisances including zoom, rotation, blur, viewpoint change, JPEG compression, light change, different rendering styles and multi-structures for comprehensive test. To further create different distributions of initial matches, a set of combinations of detector and descriptor is also taken into consideration. We measure the quality of a correspondence selection algorithm from four perspectives, i.e., precision, recall, F-measure and efficiency. According to evaluation results, the current advantages and limitations of all considered algorithms are aggregately summarized which could be treated as a "user guide" for the following developers.

Jiaqi Yang, Chen Zhao, Ke Xian et al.

This paper presents a simple yet very effective data-driven approach to fuse both low-level and high-level local geometric features for 3D rigid data matching. It is a common practice to generate distinctive geometric descriptors by fusing low-level features from various viewpoints or subspaces, or enhance geometric feature matching by leveraging multiple high-level features. In prior works, they are typically performed via linear operations such as concatenation and min pooling. We show that more compact and distinctive representations can be achieved by optimizing a neural network (NN) model under the triplet framework that non-linearly fuses local geometric features in Euclidean spaces. The NN model is trained by an improved triplet loss function that fully leverages all pairwise relationships within the triplet. Moreover, the fused descriptor by our approach is also competitive to deep learned descriptors from raw data while being more lightweight and rotational invariant. Experimental results on four standard datasets with various data modalities and application contexts confirm the advantages of our approach in terms of both feature matching and geometric registration.

Chen Zhao, Zhiguo Cao, Chi Li et al.

Feature correspondence selection is pivotal to many feature-matching based tasks in computer vision. Searching for spatially k-nearest neighbors is a common strategy for extracting local information in many previous works. However, there is no guarantee that the spatially k-nearest neighbors of correspondences are consistent because the spatial distribution of false correspondences is often irregular. To address this issue, we present a compatibility-specific mining method to search for consistent neighbors. Moreover, in order to extract and aggregate more reliable features from neighbors, we propose a hierarchical network named NM-Net with a series of convolution layers taking the generated graph as input, which is insensitive to the order of correspondences. Our experimental results have shown the proposed method achieves the state-of-the-art performance on four datasets with various inlier ratios and varying numbers of feature consistencies.