Learning procedural-aware video representations is a key step towards building agents that can reason about and execute complex tasks. Existing methods typically address this problem by aligning visual content with textual descriptions at the task and step levels to inject procedural semantics into video representations. However, due to their high level of abstraction, "task" and "step" descriptions fail to form a robust alignment with the concrete, observable details in visual data. To address this, we introduce "states", i.e., textual snapshots of object configurations, as a visually-grounded semantic layer that anchors abstract procedures to what a model can actually see. We formalize this insight in a novel Task-Step-State (TSS) framework, where tasks are achieved via steps that drive transitions between observable states. To enforce this structure, we propose a progressive pre-training strategy that unfolds the TSS hierarchy, forcing the model to first ground representations in states before associating them with steps and, ultimately, high-level tasks. Extensive experiments on the COIN and CrossTask datasets show that our method outperforms baseline models on multiple downstream tasks, including task recognition, step recognition, and next step prediction. Ablation studies show that introducing state supervision is a key driver of performance gains across all tasks. Additionally, our progressive pretraining strategy proves more effective than standard joint training, as it better enforces the intended hierarchical structure.

Understanding continuous video streams plays a fundamental role in real-time applications including embodied AI and autonomous driving. Unlike offline video understanding, streaming video understanding requires the ability to process video streams frame by frame, preserve historical information, and make low-latency decisions. To address these challenges, our main contributions are three-fold. (i) We develop a novel streaming video backbone, termed as StreamFormer, by incorporating causal temporal attention into a pre-trained vision transformer. This enables efficient streaming video processing while maintaining image representation capability. (ii) To train StreamFormer, we propose to unify diverse spatial-temporal video understanding tasks within a multitask visual-language alignment framework. Hence, StreamFormer learns global semantics, temporal dynamics, and fine-grained spatial relationships simultaneously. (iii) We conduct extensive experiments on online action detection, online video instance segmentation, and video question answering. StreamFormer achieves competitive results while maintaining efficiency, demonstrating its potential for real-time applications.

This paper presents a novel inertial localization framework named Egocentric Action-aware Inertial Localization (EAIL), which leverages egocentric action cues from head-mounted IMU signals to localize the target individual within a 3D point cloud. Human inertial localization is challenging due to IMU sensor noise that causes trajectory drift over time. The diversity of human actions further complicates IMU signal processing by introducing various motion patterns. Nevertheless, we observe that some actions captured by the head-mounted IMU correlate with spatial environmental structures (e.g., bending down to look inside an oven, washing dishes next to a sink), thereby serving as spatial anchors to compensate for the localization drift. The proposed EAIL framework learns such correlations via hierarchical multi-modal alignment with vision-language guidance. By assuming that the 3D point cloud of the environment is available, it contrastively learns modality encoders that align short-term egocentric action cues in IMU signals with local environmental features in the point cloud. The learning process is enhanced using concurrently collected vision and language signals to improve multimodal alignment. The learned encoders are then used in reasoning the IMU data and the point cloud over time and space to perform inertial localization. Interestingly, these encoders can further be utilized to recognize the corresponding sequence of actions as a by-product. Extensive experiments demonstrate the effectiveness of the proposed framework over state-of-the-art inertial localization and inertial action recognition baselines.

The existing video understanding benchmarks for multimodal large language models (MLLMs) mainly focus on short videos. The few benchmarks for long video understanding often rely on multiple-choice questions (MCQs). Due to the limitations of MCQ evaluations and the advanced reasoning abilities of MLLMs, models can often answer correctly by combining short video insights with elimination, without truly understanding the content. To bridge this gap, we introduce CG-Bench, a benchmark for clue-grounded question answering in long videos. CG-Bench emphasizes the model's ability to retrieve relevant clues, enhancing evaluation credibility. It includes 1,219 manually curated videos organized into 14 primary, 171 secondary, and 638 tertiary categories, making it the largest benchmark for long video analysis. The dataset features 12,129 QA pairs in three question types: perception, reasoning, and hallucination. To address the limitations of MCQ-based evaluation, we develop two novel clue-based methods: clue-grounded white box and black box evaluations, assessing whether models generate answers based on accurate video understanding. We evaluated multiple closed-source and open-source MLLMs on CG-Bench. The results show that current models struggle significantly with long videos compared to short ones, and there is a notable gap between open-source and commercial models. We hope CG-Bench will drive the development of more reliable and capable MLLMs for long video comprehension.

We present a framework for pre-training of 3D hand pose estimation from in-the-wild hand images sharing with similar hand characteristics, dubbed SiMHand. Pre-training with large-scale images achieves promising results in various tasks, but prior methods for 3D hand pose pre-training have not fully utilized the potential of diverse hand images accessible from in-the-wild videos. To facilitate scalable pre-training, we first prepare an extensive pool of hand images from in-the-wild videos and design our pre-training method with contrastive learning. Specifically, we collect over 2.0M hand images from recent human-centric videos, such as 100DOH and Ego4D. To extract discriminative information from these images, we focus on the similarity of hands: pairs of non-identical samples with similar hand poses. We then propose a novel contrastive learning method that embeds similar hand pairs closer in the feature space. Our method not only learns from similar samples but also adaptively weights the contrastive learning loss based on inter-sample distance, leading to additional performance gains. Our experiments demonstrate that our method outperforms conventional contrastive learning approaches that produce positive pairs solely from a single image with data augmentation. We achieve significant improvements over the state-of-the-art method (PeCLR) in various datasets, with gains of 15% on FreiHand, 10% on DexYCB, and 4% on AssemblyHands. Our code is available at https://github.com/ut-vision/SiMHand.

In egocentric video understanding, the motion of hands and objects as well as their interactions play a significant role by nature. However, existing egocentric video representation learning methods mainly focus on aligning video representation with high-level narrations, overlooking the intricate dynamics between hands and objects. In this work, we aim to integrate the modeling of fine-grained hand-object dynamics into the video representation learning process. Since no suitable data is available, we introduce HOD, a novel pipeline employing a hand-object detector and a large language model to generate high-quality narrations with detailed descriptions of hand-object dynamics. To learn these fine-grained dynamics, we propose EgoVideo, a model with a new lightweight motion adapter to capture fine-grained hand-object motion information. Through our co-training strategy, EgoVideo effectively and efficiently leverages the fine-grained hand-object dynamics in the HOD data. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple egocentric downstream tasks, including improvements of 6.3% in EK-100 multi-instance retrieval, 5.7% in EK-100 classification, and 16.3% in EGTEA classification in zero-shot settings. Furthermore, our model exhibits robust generalization capabilities in hand-object interaction and robot manipulation tasks.

Generating videos in the first-person perspective has broad application prospects in the field of augmented reality and embodied intelligence. In this work, we explore the cross-view video prediction task, where given an exo-centric video, the first frame of the corresponding ego-centric video, and textual instructions, the goal is to generate future frames of the ego-centric video. Inspired by the notion that hand-object interactions (HOI) in ego-centric videos represent the primary intentions and actions of the current actor, we present EgoExo-Gen that explicitly models the hand-object dynamics for cross-view video prediction. EgoExo-Gen consists of two stages. First, we design a cross-view HOI mask prediction model that anticipates the HOI masks in future ego-frames by modeling the spatio-temporal ego-exo correspondence. Next, we employ a video diffusion model to predict future ego-frames using the first ego-frame and textual instructions, while incorporating the HOI masks as structural guidance to enhance prediction quality. To facilitate training, we develop a fully automated pipeline to generate pseudo HOI masks for both ego- and exo-videos by exploiting vision foundation models. Extensive experiments demonstrate that our proposed EgoExo-Gen achieves better prediction performance compared to previous video prediction models on the public Ego-Exo4D and H2O benchmark datasets, with the HOI masks significantly improving the generation of hands and interactive objects in the ego-centric videos.

Egocentric object-interaction anticipation is critical for applications like augmented reality and robotics, but existing methods struggle with misaligned egocentric encoding, insufficient supervision, and underutilized historical context. These limitations stem from a lack of focus on retention, i.e., retaining long-term object-centric interactions, and prediction, i.e., future-centric encoding and future uncertainty modeling. We introduce EgoAnticipator, a novel Retentive and Predictive Learning framework that addresses these challenges. Our approach combines retentive pre-training for domain-specific encoding, predictive pre-training for future uncertainty modeling, and mirror distillation to transfer future-informed knowledge. Additionally, we propose long-term memory prompting to integrate historical interaction cues. We evaluate the effectiveness of our framework using the Ego4D short-term object interaction anticipation benchmark, covering both STAv1 and STAv2. Extensive experiments demonstrate that our framework outperforms existing methods, while ablation studies highlight the effectiveness of each design inside our retentive and predictive learning framework.

Transferring and integrating knowledge across first-person (egocentric) and third-person (exocentric) viewpoints is intrinsic to human intelligence, enabling humans to learn from others and convey insights from their own experiences. Despite rapid progress in multimodal large language models (MLLMs), their ability to perform such cross-view reasoning remains unexplored. To address this, we introduce EgoExoBench, the first benchmark for egocentric exocentric video understanding and reasoning. Built from publicly available datasets, EgoExoBench comprises over 7300 question–answer pairs spanning eleven sub-tasks organized into three core challenges: semantic alignment, viewpoint association, and temporal reasoning. We evaluate 13 state-of-the-art MLLMs and find that while these models excel on single-view tasks, they struggle to align semantics across perspectives, accurately associate views, and infer temporal dynamics in the ego-exo context. We hope EgoExoBench can serve as a valuable resource for research on embodied agents and intelligent assistants seeking human-like cross-view intelligence.

Egocentric video reasoning centers on an unobservable agent behind the camera who dynamically shapes the environment, requiring inference of hidden intentions and recognition of fine-grained interactions. This core challenge limits current multimodal large language models (MLLMs), which excel at visible event reasoning but lack embodied, first-person understanding. To bridge this gap, we introduce EgoThinker, a novel framework that endows MLLMs with robust egocentric reasoning capabilities through spatio-temporal chain-of-thought supervision and a two-stage learning curriculum. First, we introduce EgoRe-5M, a large-scale egocentric QA dataset constructed from 13M diverse egocentric video clips. This dataset features multi-minute segments annotated with detailed CoT rationales and dense hand–object grounding. Second, we employ SFT on EgoRe-5M to instill reasoning skills, followed by reinforcement fine-tuning (RFT) to further enhance spatio-temporal localization. Experimental results show that EgoThinker outperforms existing methods across multiple egocentric benchmarks, while achieving substantial improvements in fine-grained spatio-temporal localization tasks.

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. https://ego-exo4d-data.org/

Abstract Audio-Visual Question Answering (AVQA) requires the model to answer questions with complex dynamic audio-visual information. Prior works on this task mainly consider only using single question-answer pairs during training, overlooking the rich semantic associations between questions. In this work, we propose a novel Collective Question-Guided Network (CoQo), which accepts multiple question-answer pairs as input and leverages the reasoning over these questions to assist the model training process. The core module is the proposed Question Guided Transformer (QGT), which uses collective question reasoning to perform question-guided feature extraction. Since multiple question-answer pairs are not always available, especially during inference, our QGT uses a set of learnable tokens to learn the collective information from multiple questions during training. At inference time, these learnable tokens bring additional reasoning information even when only one question is used as input. We employ QGT in both spatial and temporal dimensions to extract question-related features effectively and efficiently. To better capture detailed audio-visual associations, we train the model in a finer level by distinguishing feature pairs of different questions within the same video. Extensive experiments demonstrate that our method can achieve state-of-the-art performance on three AVQA datasets while reducing training time significantly. We also observe strong performances of our method on three VQA benchmarks. Detailed ablation studies further confirm the effectiveness of our proposed collective question reasoning scheme, both quantitatively and qualitatively.

Abstract In the development of science, accurate and reproducible documentation of the experimental process is crucial. Automatic recognition of the actions in experiments from videos would help experimenters by complementing the recording of experiments. Towards this goal, we propose FineBio, a new fine-grained video dataset of people performing biological experiments. The dataset consists of multi-view videos of 32 participants performing mock biological experiments with a total duration of 14.5 hours. One experiment forms a hierarchical structure, where a protocol consists of several steps, each further decomposed into a set of atomic operations. The uniqueness of biological experiments is that while they require strict adherence to steps described in each protocol, there is freedom in the order of atomic operations. We provide hierarchical annotation on protocols, steps, atomic operations, object locations, and their manipulation states, providing new challenges for structured activity understanding and hand-object interaction recognition. To find out challenges on activity understanding in biological experiments, we introduce baseline models and results on four different tasks, including (i) step segmentation, (ii) atomic operation detection (iii) object detection, and (iv) manipulated/affected object detection. Dataset and code are available from https://github.com/aistairc/FineBio .

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.

The task of weakly supervised temporal sentence grounding (WSTSG) aims to detect temporal intervals corresponding to a language description from untrimmed videos with only video-level video-language correspondence. For an anchor sample, most existing approaches generate negative samples either from other videos or within the same video for contrastive learning. However, some training samples are highly similar to the anchor sample, directly regarding them as negative samples leads to difficulties for optimization and ignores the correlations between these similar samples and the anchor sample. To address this, we propose Positive Sample Mining (PSM), a novel framework that mines positive samples from the training set to provide more discriminative supervision. Specifically, for a given anchor sample, we partition the remaining training set into semantically similar and dissimilar subsets based on the similarity of their text queries. To effectively leverage these correlations, we introduce a PSM-guided contrastive loss to ensure that the anchor proposal is closer to similar samples and further from dissimilar ones. Additionally, we design a PSM-guided rank loss to ensure that similar samples are closer to the anchor proposal than to the negative intra-video proposal, aiming to distinguish the anchor proposal and the negative intra-video proposal. Experiments on the WSTSG and grounded VideoQA tasks demonstrate the effectiveness and superiority of our method.

Weakly supervised temporal sentence grounding aims to temporally locate events described by a sentence in a video, relying solely on video-level visual-language correspondences. Because of the absence of precise boundary information, existing works primarily focus on multiple instance learning methods to establish segment-level video-language alignment. In this work, we propose Prompt-augmented Boundary Attentive Learning (PBAL) to enable the explicit modeling of the segment boundaries in a weakly supervised context. To represent the boundaries with sentences, we first generate sentences describing the start and end of an event, leveraging the capabilities of large language models (LLMs). With the augmented sentences, we then model the boundary-level video-language correspondence using a novel boundary-attentive learning module. This module generates probability maps of the starting and ending points, and is learned through boundary type prediction and self-supervised reconstruction. Experiments on two standard datasets, Charades-STA [1] and ActivityNet Captions [2] demonstrate PBAL’s state-of-the-art performance. The results of our ablation study further demonstrate the effectiveness of our boundary-attentive learning and prompt augmentation techniques.

We present Ego-Exo4D, a diverse, large-scale multi-modal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured ego-centric 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 un-precedented: 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.

Being able to map the activities of others into one's own point of view is a fundamental human skill even from a very early age. Taking a step toward understanding this human ability, we introduce EgoExoLearn, a large-scale dataset that emulates the human demonstration following process, in which individuals record egocentric videos as they execute tasks guided by exocentric-view demonstration videos. Focusing on the potential applications in daily assistance and professional support, EgoExoLearn contains egocentric and demonstration video data spanning 120 hours captured in daily life scenarios and specialized laboratories. Along with the videos we record high-quality gaze data and provide detailed multimodal annotations, formulating a playground for modeling the human ability to bridge asynchronous procedural actions from different viewpoints. To this end, we present benchmarks such as crossview association, cross-view action planning, and crossview referenced skill assessment, along with detailed analysis. We expect EgoExoLearn can serve as an important resource for bridging the actions across views, thus paving the way for creating AI agents capable of seamlessly learning by observing humans in the real world. The dataset and benchmark codes are available at https://github.com/OpenGVLab/EgoExoLearn.

Understanding human actions from videos offirst-person view poses significant challenges. Most prior approaches explore representation learning on egocentric videos only, while overlooking the potential benefit of exploiting existing large-scale third-person videos. In this paper, (1) we develop EgoInstructor, a retrieval-augmented multimodal captioning model that automatically retrieves semantically relevant third-person instructional videos to enhance the video captioning of egocentric videos, (2) for training the cross-view retrieval module, we devise an au-tomatic pipeline to discover ego-exo video pairs from distinct large-scale egocentric and exocentric datasets, (3) we train the cross-view retrieval module with a novel EgoEx-oNCE loss that pulls egocentric and exocentric video features closer, by aligning them to shared text features that describe similar actions, (4) through extensive experiments, our cross-view retrieval module demonstrates superior performance across seven benchmarks. Regarding egocen-tric video captioning, EgoInstructor exhibits significant improvements by leveraging third-person videos as references.

Abstract The task of few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. How to better describe the action in each video and how to compare the similarity between videos are two of the most critical factors in this task. Directly describing the video globally or by its individual frames cannot well represent the spatiotemporal dependencies within an action. On the other hand, naively matching the global representations of two videos is also not optimal since action can happen at different locations in a video with different speeds. In this work, we propose a novel approach that describes each video using multiple types of prototypes and then computes the video similarity with a particular matching strategy for each type of prototypes. To better model the spatiotemporal dependency, we describe the video by generating prototypes that model the multi-level spatiotemporal relations via transformers. There are a total of three types of prototypes. The first type of prototypes are trained to describe specific aspects of the action in the video e.g., the start of the action, regardless of its timestamp. These prototypes are directly matched one-to-one between two videos to compare their similarity. The second type of prototypes are the timestamp-centered prototypes that are trained to focus on specific timestamps of the video. To deal with the temporal variation of actions in a video, we apply bipartite matching to allow the matching of prototypes of different timestamps. The third type of prototypes are generated from the timestamp-centered prototypes, which regularize their temporal consistency while serving as an auxiliary summarization of the whole video. Experiments demonstrate that our proposed method achieves state-of-the-art results on multiple benchmarks.

The Multiplane Image (MPI), containing a set of fronto-parallel$RGB_{\alpha}$layers, is an effective and efficient representation for view synthesis from sparse inputs. Yet, its fixed structure limits the performance, especially for surfaces imaged at oblique angles. We introduce the Structural MPI (S-MPI), where the plane structure approximates 3D scenes concisely. Conveying$RGB_{\alpha}$contexts with geometrically-faithful structures, the S-MPI directly bridges view synthe-sis and 3D reconstruction. It can not only overcome the critical limitations of MPI, i.e., discretization artifacts from sloped surfaces and abuse of redundant layers, and can also acquire planar 3D reconstruction. Despite the intu-ition and demand of applying S-MPI, great challenges are introduced,$e.g$., high-fidelity approximation for both$RGB_{\alpha}$layers and plane poses, multi-view consistency, non-planar regions modeling, and efficient rendering with intersected planes. Accordingly, we propose a transformer-based network based on a segmentation model [4]. It predicts compact and expressive S-MPI layers with their corresponding masks, poses, and$RGB_{\alpha}$contexts. Non-planar regions are inclusively handled as a special case in our unified frame-work. Multi-view consistency is ensured by sharing global proxy embeddings, which encode plane-level features cov-ering the complete 3D scenes with aligned coordinates. In-tensive experiments show that our method outperforms both previous state-of-the-art MPI-based view synthesis methods and planar reconstruction methods.

The task of weakly supervised temporal sentence grounding aims at finding the corresponding temporal moments of a language description in the video, given video-language correspondence only at video-level. Most existing works select mismatched video-language pairs as negative samples and train the model to generate better positive proposals that are distinct from the negative ones. However, due to the complex temporal structure of videos, proposals distinct from the negative ones may correspond to several video segments but not necessarily the correct ground truth. To alleviate this problem, we propose an uncertainty-guided self-training technique to provide extra self-supervision signal to guide the weakly-supervised learning. The self-training process is based on teacher-student mutual learning with weak-strong augmentation, which enables the teacher network to generate relatively more reliable outputs compared to the student network, so that the student network can learn from the teacher's output. Since directly applying existing self-training methods in this task easily causes error accumulation, we specifically design two techniques in our selftraining method: (1) we construct a Bayesian teacher network, leveraging its uncertainty as a weight to suppress the noisy teacher supervisory signals; (2) we leverage the cycle consistency brought by temporal data augmentation to perform mutual learning between the two networks. Experiments demonstrate our method's superiority on Charades-STA and ActivityNet Captions datasets. We also show in the experiment that our self-training method can be applied to improve the performance of multiple backbone methods.

Most existing forecasting systems are memory-based methods, which attempt to mimic human forecasting ability by employing various memory mechanisms and have progressed in temporal modeling for memory dependency. Nevertheless, an obvious weakness of this paradigm is that it can only model limited historical dependence and can not transcend the past. In this paper, we rethink the temporal dependence of event evolution and propose a novel memory-anticipation-based paradigm to model an entire temporal structure, including the past, present, and future. Based on this idea, we present Memory-and-Anticipation Transformer (MAT), a memory-anticipation-based approach, to address the online action detection and anticipation tasks. In addition, owing to the inherent superiority of MAT, it can process online action detection and anticipation tasks in a unified manner. The proposed MAT model is tested on four challenging benchmarks TVSeries, THUMOS’14, HDD, and EPIC-Kitchens-100, for online action detection and anticipation tasks, and it significantly outperforms all existing methods. Code is available at https://github.com/Echo0125/Memory-and-Anticipation-Transformer.

Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human motor capacity and objects’ physical property thus benefiting tasks such as action anticipation and robot imitation learning. However, the definition of affordance in existing datasets often: 1) mix up affordance with object functionality; 2) confuse affordance with goal-related action; and 3) ignore human motor capacity. This paper proposes an efficient annotation scheme to address these issues by combining goal-irrelevant motor actions and grasp types as affordance labels and introducing the concept of mechanical action to represent the action possibilities between two objects. We provide new annotations by applying this scheme to the EPIC-KITCHENS dataset and test our annotation with tasks such as affordance recognition, hand-object interaction hotspots prediction, and cross-domain evaluation of affordance. The results show that models trained with our annotation can distinguish affordance from other concepts, predict fine-grained interaction possibilities on objects, and generalize through different do-mains.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of dailylife 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/

Unsupervised domain adaptive video action recognition aims to recognize actions of a target domain using a model trained with only out-of-domain (source) annotations. The inherent complexity of videos makes this task challenging but also provides ground for leveraging multi-modal inputs (e.g., RGB, Flow, Audio). Most previous works utilize the multi-modal information by either aligning each modality individually or learning representation via cross-modal self-supervision. Different from previous works, we find that the cross-domain alignment can be more effectively done by using cross-modal interaction first. Cross-modal knowledge interaction allows other modalities to supplement missing transferable information because of the cross-modal complementarity. Also, the most transferable aspects of data can be highlighted using cross-modal consensus. In this work, we present a novel model that jointly considers these two characteristics for domain adaptive action recognition. We achieve this by implementing two modules, where the first module exchanges complementary transferable information across modalities through the semantic space, and the second module finds the most transferable spatial region based on the consensus of all modalities. Extensive experiments validate that our proposed method can significantly outperform state-of-the-art methods on multiple benchmark datasets, including the complex fine-grained dataset EPIC-Kitchens-100.

As the population ages, many will acquire visual impairments. To improve design for these users, it is essential to build awareness of their perspective during everyday routines, especially for design students.

The attribution method provides a direction for interpreting opaque neural networks in a visual way by identifying and visualizing the input regions/pixels that dominate the output of a network. Regarding the attribution method for visually explaining video understanding networks, it is challenging because of the unique spatiotemporal dependencies existing in video inputs and the special 3D convolutional or recurrent structures of video understanding networks. However, most existing attribution methods focus on explaining networks taking a single image as input and a few works specifically devised for video attribution come short of dealing with diversified structures of video understanding networks. In this paper, we investigate a generic perturbation-based attribution method that is compatible with diversified video understanding networks. Besides, we propose a novel regularization term to enhance the method by constraining the smoothness of its attribution results in both spatial and temporal dimensions. In order to assess the effectiveness of different video attribution methods without relying on manual judgement, we introduce reliable objective metrics which are checked by a newly proposed reliability measurement. We verified the effectiveness of our method by both subjective and objective evaluation and comparison with multiple significant attribution methods.

Visual storytelling is a task of generating relevant and interesting stories for given image sequences. In this work we aim at increasing the diversity of the generated stories while preserving the informative content from the images. We propose to foster the diversity and informativeness of a generated story by using a concept selection module that suggests a set of concept candidates. Then, we utilize a large scale pre-trained model to convert concepts and images into full stories. To enrich the candidate concepts, a commonsense knowledge graph is created for each image sequence from which the concept candidates are proposed. To obtain appropriate concepts from the graph, we propose two novel modules that consider the correlation among candidate concepts and the image-concept correlation. Extensive automatic and human evaluation results demonstrate that our model can produce reasonable concepts. This enables our model to outperform the previous models by a large margin on the diversity and informativeness of the story, while retaining the relevance of the story to the image sequence.

Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen classes to unseen classes. Since semantic knowledge is built on attributes shared between different classes, which are highly local, strong prior for localization of object attribute is beneficial for visual-semantic embedding. Interestingly, when recognizing unseen images, human would also automatically gaze at regions with certain semantic clue. Therefore, we introduce a novel goal-oriented gaze estimation module (GEM) to improve the discriminative attribute localization based on the class-level attributes for ZSL. We aim to predict the actual human gaze location to get the visual attention regions for recognizing a novel object guided by attribute description. Specifically, the task-dependent attention is learned with the goal-oriented GEM, and the global image features are simultaneously optimized with the regression of local attribute features. Experiments on three ZSL benchmarks, i.e., CUB, SUN and AWA2, show the superiority or competitiveness of our proposed method against the state-of-the-art ZSL methods. The ablation analysis on real gaze data CUB-VWSW also validates the benefits and accuracy of our gaze estimation module. This work implies the promising benefits of collecting human gaze dataset and automatic gaze estimation algorithms on high-level computer vision tasks. The code is available at https://github.com/osierboy/GEM-ZSL.

In industrial assembly tasks, the in-hand pose of grasped objects needs to be known with high precision for subsequent manipulation tasks such as insertion. This problem (in-hand-pose estimation) has traditionally been addressed using visual recognition or tactile sensing. On the one hand, while visual recognition can provide efficient pose estimates, it tends to suffer from low precision due to noise, occlusions and calibration errors. On the other hand, tactile fingertip sensors can provide precise complementary information, but their low durability significantly limits their use in real-world applications. To get the best of both worlds, we propose an efficient method for in-hand pose estimation using off-the-shelf cameras and robot wrist force sensors, which requires no precise camera calibration. The key idea is to utilize visual and contact information adaptively to maximally reduce the uncertainty about the in-hand object pose in a Bayesian state estimation framework. As most of the uncertainty can be resolved from visual observations, our approach reduces the number of physical environment interactions while keeping a high pose estimation accuracy. Our experimental evaluation demonstrates that our approach can estimate object poses with sub-mm precision with an off-the-shelf camera and force-torque sensor.

"Making black box models explainable " is a vital problem that accompanies the development of deep learning networks. For networks taking visual information as input, one basic but challenging explanation method is to identify and visualize the input pixels/regions that dominate the network's prediction. However, most existing works focus on explaining networks taking a single image as input and do not consider the temporal relationship that exists in videos. Providing an easy-to-use visual explanation method that is applicable to diversified structures of video understanding networks still remains an open challenge. In this paper, we investigate a generic perturbation-based method for visually explaining video understanding networks. Besides, we propose a novel loss function to enhance the method by constraining the smoothness of its results in both spatial and temporal dimensions. The method enables the comparison of explanation results between different network structures to become possible and can also avoid generating the pathological adversarial explanations for video inputs. Experimental comparison results verified the effectiveness of our method.

Temporal relations among multiple action segments play an important role in action segmentation especially when observations are limited (e.g., actions are occluded by other objects or happen outside a field of view). In this paper, we propose a network module called Graph-based Temporal Reasoning Module (GTRM) that can be built on top of existing action segmentation models to learn the relation of multiple action segments in various time spans. We model the relations by using two Graph Convolution Networks (GCNs) where each node represents an action segment. The two graphs have different edge properties to account for boundary regression and classification tasks, respectively. By applying graph convolution, we can update each node's representation based on its relation with neighboring nodes. The updated representation is then used for improved action segmentation. We evaluate our model on the challenging egocentric datasets namely EGTEA and EPIC-Kitchens, where actions may be partially observed due to the viewpoint restriction. The results show that our proposed GTRM outperforms state-of-the-art action segmentation models by a large margin. We also demonstrate the effectiveness of our model on two third-person video datasets, the 50Salads dataset and the Breakfast dataset.

Joint attention often happens during social interactions, in which individuals share focus on the same object. This article proposes an egocentric vision-based system (ego-vision system) that aims to discover the objects looked at jointly by a group of persons engaged in interactive activities. The proposed system relies on a collection of wearable eye-tracking cameras that provide an egocentric view of the interaction scenes as well as points-of-gaze measurement of each participant. Technically in our system, we develop a hierarchical conditional random field (CRF) based graphical model that can temporally localize joint attention periods and spatially segment objects of joint attention. By solving these two coupled tasks together in an iterative optimization procedure, we show that human joint attention can be reliably discovered from videos even with cluttered background and noisy gaze measurement. A new dataset of joint attention is collected and annotated for evaluating the two tasks of joint attention where two to four persons are involved. Experimental results demonstrate that our approach achieves state-of-the-art performance on both tasks of spatial segmentation and temporal localization of joint attention.

In this work, we address two coupled tasks of gaze prediction and action recognition in egocentric videos by exploring their mutual context: the information from gaze prediction facilitates action recognition and vice versa. Our assumption is that during the procedure of performing a manipulation task, on the one hand, what a person is doing determines where the person is looking at. On the other hand, the gaze location reveals gaze regions which contain important and information about the undergoing action and also the non-gaze regions that include complimentary clues for differentiating some fine-grained actions. We propose a novel mutual context network (MCN) that jointly learns action-dependent gaze prediction and gaze-guided action recognition in an end-to-end manner. Experiments on multiple egocentric video datasets demonstrate that our MCN achieves state-of-the-art performance of both gaze prediction and action recognition. The experiments also show that action-dependent gaze patterns could be learned with our method.