Abstract:Delving into the realm of egocentric vision, the advancement of referring video object segmentation (RVOS) stands as pivotal in understanding human activities. However, existing RVOS task primarily relies on static attributes such as object names to segment target objects, posing challenges in distinguishing target objects from background objects and in identifying objects undergoing state changes. To address these problems, this work proposes a novel action-aware RVOS setting called ActionVOS, aiming at segmenting only active objects in egocentric videos using human actions as a key language prompt. This is because human actions precisely describe the behavior of humans, thereby helping to identify the objects truly involved in the interaction and to understand possible state changes. We also build a method tailored to work under this specific setting. Specifically, we develop an action-aware labeling module with an efficient action-guided focal loss. Such designs enable ActionVOS model to prioritize active objects with existing readily-available annotations. Experimental results on VISOR dataset reveal that ActionVOS significantly reduces the mis-segmentation of inactive objects, confirming that actions help the ActionVOS model understand objects' involvement. Further evaluations on VOST and VSCOS datasets show that the novel ActionVOS setting enhances segmentation performance when encountering challenging circumstances involving object state changes. We will make our implementation available at https://github.com/ut-vision/ActionVOS.
Abstract:Temporally localizing the presence of object states in videos is crucial in understanding human activities beyond actions and objects. This task has suffered from a lack of training data due to object states' inherent ambiguity and variety. To avoid exhaustive annotation, learning from transcribed narrations in instructional videos would be intriguing. However, object states are less described in narrations compared to actions, making them less effective. In this work, we propose to extract the object state information from action information included in narrations, using large language models (LLMs). Our observation is that LLMs include world knowledge on the relationship between actions and their resulting object states, and can infer the presence of object states from past action sequences. The proposed LLM-based framework offers flexibility to generate plausible pseudo-object state labels against arbitrary categories. We evaluate our method with our newly collected Multiple Object States Transition (MOST) dataset including dense temporal annotation of 60 object state categories. Our model trained by the generated pseudo-labels demonstrates significant improvement of over 29% in mAP against strong zero-shot vision-language models, showing the effectiveness of explicitly extracting object state information from actions through LLMs.
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.
Abstract: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). More than 800 participants from 13 cities worldwide performed these activities in 131 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,422 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 will be open sourced to fuel new research in the community.
Abstract:We propose a novel benchmark for cross-view knowledge transfer of dense video captioning, adapting models from web instructional videos with exocentric views to an egocentric view. While dense video captioning (predicting time segments and their captions) is primarily studied with exocentric videos (e.g., YouCook2), benchmarks with egocentric videos are restricted due to data scarcity. To overcome the limited video availability, transferring knowledge from abundant exocentric web videos is demanded as a practical approach. However, learning the correspondence between exocentric and egocentric views is difficult due to their dynamic view changes. The web videos contain mixed views focusing on either human body actions or close-up hand-object interactions, while the egocentric view is constantly shifting as the camera wearer moves. This necessitates the in-depth study of cross-view transfer under complex view changes. In this work, we first create a real-life egocentric dataset (EgoYC2) whose captions are shared with YouCook2, enabling transfer learning between these datasets assuming their ground-truth is accessible. To bridge the view gaps, we propose a view-invariant learning method using adversarial training in both the pre-training and fine-tuning stages. While the pre-training is designed to learn invariant features against the mixed views in the web videos, the view-invariant fine-tuning further mitigates the view gaps between both datasets. We validate our proposed method by studying how effectively it overcomes the view change problem and efficiently transfers the knowledge to the egocentric domain. Our benchmark pushes the study of the cross-view transfer into a new task domain of dense video captioning and will envision methodologies to describe egocentric videos in natural language.
Abstract:Object detectors do not work well when domains largely differ between training and testing data. To solve this problem, domain generalization approaches, which require training data with ground-truth labels from multiple domains, have been proposed. However, it is time-consuming and labor-intensive to collect those data for object detection because not only class labels but also bounding boxes must be annotated. To overcome the problem of domain gap in object detection without requiring expensive annotations, we propose to consider two new problem settings: semi-supervised domain generalizable object detection (SS-DGOD) and weakly-supervised DGOD (WS-DGOD). In contrast to the conventional domain generalization for object detection that requires labeled data from multiple domains, SS-DGOD and WS-DGOD require labeled data only from one domain and unlabeled or weakly-labeled data from multiple domains for training. We show that object detectors can be effectively trained on the proposed settings with the same student-teacher learning framework, where a student network is trained with pseudo labels output from a teacher on the unlabeled or weakly-labeled data. The experimental results demonstrate that the object detectors trained on the proposed settings significantly outperform baseline detectors trained on one labeled domain data and perform comparably to or better than those trained on unsupervised domain adaptation (UDA) settings, while ours do not use target domain data for training in contrast to UDA.
Abstract:Point-level supervised temporal action localization (PTAL) aims at recognizing and localizing actions in untrimmed videos where only a single point (frame) within every action instance is annotated in training data. Without temporal annotations, most previous works adopt the multiple instance learning (MIL) framework, where the input video is segmented into non-overlapped short snippets, and action classification is performed independently on every short snippet. We argue that the MIL framework is suboptimal for PTAL because it operates on separated short snippets that contain limited temporal information. Therefore, the classifier only focuses on several easy-to-distinguish snippets instead of discovering the whole action instance without missing any relevant snippets. To alleviate this problem, we propose a novel method that localizes actions by generating and evaluating action proposals of flexible duration that involve more comprehensive temporal information. Moreover, we introduce an efficient clustering algorithm to efficiently generate dense pseudo labels that provide stronger supervision, and a fine-grained contrastive loss to further refine the quality of pseudo labels. Experiments show that our proposed method achieves competitive or superior performance to the state-of-the-art methods and some fully-supervised methods on four benchmarks: ActivityNet 1.3, THUMOS 14, GTEA, and BEOID datasets.
Abstract: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 domains.
Abstract:Object affordance is an important concept in human-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, 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. We qualitatively verify that models trained with our annotation can distinguish affordance and mechanical actions.
Abstract:In this survey, we present comprehensive analysis of 3D hand pose estimation from the perspective of efficient annotation and learning. In particular, we study recent approaches for 3D hand pose annotation and learning methods with limited annotated data. In 3D hand pose estimation, collecting 3D hand pose annotation is a key step in developing hand pose estimators and their applications, such as video understanding, AR/VR, and robotics. However, acquiring annotated 3D hand poses is cumbersome, e.g., due to the difficulty of accessing 3D information and occlusion. Motivated by elucidating how recent works address the annotation issue, we investigated annotation methods classified as manual, synthetic-model-based, hand-sensor-based, and computational approaches. Since these annotation methods are not always available on a large scale, we examined methods of learning 3D hand poses when we do not have enough annotated data, namely self-supervised pre-training, semi-supervised learning, and domain adaptation. Based on the analysis of these efficient annotation and learning, we further discuss limitations and possible future directions of this field.