Related papers: Unsupervised Pre-training for Temporal Action Loca…
Temporal grounding of natural language in untrimmed videos is a fundamental yet challenging multimedia task facilitating cross-media visual content retrieval. We focus on the weakly supervised setting of this task that merely accesses to…
Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need…
A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias. While most existing works implicitly achieve this with video-specific pretext tasks (e.g., predicting…
This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones. The proposed UL layers can play two roles: they can be the cost function…
In this paper we address the problem of automatically discovering atomic actions in unsupervised manner from instructional videos, which are rarely annotated with atomic actions. We present an unsupervised approach to learn atomic actions…
Weakly-supervised temporal action localization (WS-TAL) aims to localize actions in untrimmed videos with only video-level labels. Most existing models follow the "localization by classification" procedure: locate temporal regions…
Temporal action segmentation in videos has drawn much attention recently. Timestamp supervision is a cost-effective way for this task. To obtain more information to optimize the model, the existing method generated pseudo frame-wise labels…
In this work, we tackle the challenging problem of unsupervised video domain adaptation (UVDA) for action recognition. We specifically focus on scenarios with a substantial domain gap, in contrast to existing works primarily deal with small…
This paper proposes a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN), which uses the domain-collaborative and domain-adversarial learning strategy for training the neural network. The…
We propose a self-supervised visual learning method by predicting the variable playback speeds of a video. Without semantic labels, we learn the spatio-temporal visual representation of the video by leveraging the variations in the visual…
This technical report presents an overview of our solution used in the submission to ActivityNet Challenge 2020 Task 1 (\textbf{temporal action localization/detection}). Temporal action localization requires to not only precisely locate the…
We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to…
The goal of few-shot video classification is to learn a classification model with good generalization ability when trained with only a few labeled videos. However, it is difficult to learn discriminative feature representations for videos…
The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections. To alleviate this problem, in this paper, we propose…
Recent advancements in deep generative models have facilitated the creation of photo-realistic images across various tasks. However, these generated images often exhibit perceptual artifacts in specific regions, necessitating manual…
Recent approaches leveraging multi-modal pre-trained models like CLIP for Unsupervised Domain Adaptation (UDA) have shown significant promise in bridging domain gaps and improving generalization by utilizing rich semantic knowledge and…
Temporal Action Localization (TAL) requires identifying both the boundaries and categories of actions in untrimmed videos. While vision-language models (VLMs) offer rich semantics to complement visual evidence, existing approaches tend to…
In this paper, we study an intermediate form of supervision, i.e., single-frame supervision, for temporal action localization (TAL). To obtain the single-frame supervision, the annotators are asked to identify only a single frame within the…
Temporal action localization (TAL) is a task of identifying a set of actions in a video, which involves localizing the start and end frames and classifying each action instance. Existing methods have addressed this task by using predefined…
This work addresses the problem of Social Activity Recognition (SAR), a critical component in real-world tasks like surveillance and assistive robotics. Unlike traditional event understanding approaches, SAR necessitates modeling individual…