相关论文: MMAD: Multi-label Micro-Action Detection in Videos

Online action detection (OAD) aims to identify ongoing actions from streaming video in real-time, without access to future frames. Since these actions manifest at varying scales of granularity, ranging from coarse to fine, projecting an…

We make available to the community a new dataset to support action-recognition research. This dataset is different from prior datasets in several key ways. It is significantly larger. It contains streaming video with long segments…

Temporal Activity Detection aims to predict activity classes per frame, in contrast to video-level predictions in Activity Classification (i.e., Activity Recognition). Due to the expensive frame-level annotations required for detection, the…

We present a dual-pathway approach for recognizing fine-grained interactions from videos. We build on the success of prior dual-stream approaches, but make a distinction between the static and dynamic representations of objects and their…

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…

Many videos depict people, and it is their interactions that inform us of their activities, relation to one another and the cultural and social setting. With advances in human action recognition, researchers have begun to address the…

Temporal Action Detection (TAD) is an essential and challenging topic in video understanding, aiming to localize the temporal segments containing human action instances and predict the action categories. The previous works greatly rely upon…

Recognizing human actions in videos requires spatial and temporal understanding. Most existing action recognition models lack a balanced spatio-temporal understanding of videos. In this work, we propose a novel two-stream architecture,…

Video action recognition is a challenging but important task for understanding and discovering what the video does. However, acquiring annotations for a video is costly, and semi-supervised learning (SSL) has been studied to improve…

Automatic analysis of the video is one of most complex problems in the fields of computer vision and machine learning. A significant part of this research deals with (human) activity recognition (HAR) since humans, and the activities that…

Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing…

Multimodal multiview learning seeks to integrate information from diverse sources to enhance task performance. Existing approaches often struggle with flexible view configurations, including arbitrary view combinations, numbers of views,…

Understanding Activities of Daily Living (ADLs) is a crucial step for different applications including assistive robots, smart homes, and healthcare. However, to date, few benchmarks and methods have focused on complex ADLs, especially…

Every moment counts in action recognition. A comprehensive understanding of human activity in video requires labeling every frame according to the actions occurring, placing multiple labels densely over a video sequence. To study this…

The analysis of the ubiquitous human-human interactions is pivotal for understanding humans as social beings. Existing human-human interaction datasets typically suffer from inaccurate body motions, lack of hand gestures and fine-grained…

Traffic Atomic Activity which describes traffic patterns for topological intersection dynamics is a crucial topic for the advancement of intelligent driving systems. However, existing atomic activity datasets are collected from an…

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot…

Markerless motion capture and understanding of professional non-daily human movements is an important yet unsolved task, which suffers from complex motion patterns and severe self-occlusion, especially for the monocular setting. In this…

Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of…

This paper is the first work to perform spatio-temporal mapping of human activity using the visual content of geo-tagged videos. We utilize a recent deep-learning based video analysis framework, termed hidden two-stream networks, to…