Related papers: CoLo-CAM: Class Activation Mapping for Object Co-L…
Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation (WSSS), allowing the localization of object regions in an image using only image-level labels. However, existing CAM methods suffer from…
Video action localization aims to find the timings of specific actions from a long video. Although existing learning-based approaches have been successful, they require annotating videos, which comes with a considerable labor cost. This…
Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels. Currently, most state-of-the-art WSTAL methods follow a Multi-Instance Learning (MIL) pipeline: producing…
Localizing actions in video is a core task in computer vision. The weakly supervised temporal localization problem investigates whether this task can be adequately solved with only video-level labels, significantly reducing the amount of…
Most activity localization methods in the literature suffer from the burden of frame-wise annotation requirement. Learning from weak labels may be a potential solution towards reducing such manual labeling effort. Recent years have…
We present an architecture and a training recipe that adapts pre-trained open-world image models to localization in videos. Understanding the open visual world (without being constrained by fixed label spaces) is crucial for many real-world…
We introduce Correspondence-Oriented Imitation Learning (COIL), a conditional policy learning framework for visuomotor control with a flexible task representation in 3D. At the core of our approach, each task is defined by the intended…
Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this paper, we present…
Addressing multi-label action recognition in videos represents a significant challenge for robotic applications in dynamic environments, especially when the robot is required to cooperate with humans in tasks that involve objects. Existing…
This study examined whether a single ceiling-mounted camera could be used to capture fine-grained learning behaviours in co-located practical learning. In undergraduate nursing simulations, teachers first identified seven observable…
Video anomaly detection under video-level labels is currently a challenging task. Previous works have made progresses on discriminating whether a video sequencecontains anomalies. However, most of them fail to accurately localize the…
Convolutional neural networks have been shown to develop internal representations, which correspond closely to semantically meaningful objects and parts, although trained solely on class labels. Class Activation Mapping (CAM) is a recent…
Video Correlation Learning (VCL), which aims to analyze the relationships between videos, has been widely studied and applied in various general video tasks. However, applying VCL to instructional videos is still quite challenging due to…
Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training. Such visualization methods, including class activation mapping (CAM)…
Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an…
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors. Many WSOD approaches adopt multiple instance learning…
Temporal action localization is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of action instances. However, it is expensive and…
Temporal action localization (TAL) is a prevailing task due to its great application potential. Existing works in this field mainly suffer from two weaknesses: (1) They often neglect the multi-label case and only focus on temporal modeling.…
Recent breakthroughs in Multimodal Large Language Models (MLLMs) have gained significant recognition within the deep learning community, where the fusion of the Video Foundation Models (VFMs) and Large Language Models(LLMs) has proven…
We introduce the task of weakly supervised learning for detecting human and object interactions in videos. Our task poses unique challenges as a system does not know what types of human-object interactions are present in a video or the…