Related papers: Probabilistic Temporal Masked Attention for Cross-…
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…
Transformers have become prevalent in computer vision due to their performance and flexibility in modelling complex operations. Of particular significance is the 'cross-attention' operation, which allows a vector representation (e.g. of an…
Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions, addressing real-world dynamism. Existing CTTA methods mainly rely on entropy minimization or…
This paper addresses the task of unsupervised video multi-object segmentation. Current approaches follow a two-stage paradigm: 1) detect object proposals using pre-trained Mask R-CNN, and 2) conduct generic feature matching for temporal…
Universal domain adaptation (UniDA) aims to transfer knowledge from the source domain to the target domain without any prior knowledge about the label set. The challenge lies in how to determine whether the target samples belong to common…
The rapid advancement of sensor technologies and artificial intelligence are creating new opportunities for traffic safety enhancement. Dashboard cameras (dashcams) have been widely deployed on both human driving vehicles and automated…
Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs). However, effective and efficient methods for incorporation of…
Typical techniques for sequence classification are designed for well-segmented sequences which have been edited to remove noisy or irrelevant parts. Therefore, such methods cannot be easily applied on noisy sequences expected in real-world…
Semi-supervised temporal action segmentation (SS-TA) aims to perform frame-wise classification in long untrimmed videos, where only a fraction of videos in the training set have labels. Recent studies have shown the potential of contrastive…
Advertising channels have evolved from conventional print media, billboards and radio advertising to online digital advertising (ad), where the users are exposed to a sequence of ad campaigns via social networks, display ads, search etc.…
Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. However, directly modeling the contextual information between…
Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. The unclear boundaries of actions in videos often result in imprecise predictions of action boundaries by…
Multimodal Large Language Models (MLLMs) have significantly improved performance across various image-language applications. Recently, there has been a growing interest in adapting image pre-trained MLLMs for video-related tasks. However,…
Video summarization is among challenging tasks in computer vision, which aims at identifying highlight frames or shots over a lengthy video input. In this paper, we propose an novel attention-based framework for video summarization with…
Action understanding, encompassing action detection and anticipation, plays a crucial role in numerous practical applications. However, untrimmed videos are often characterized by substantial redundant information and noise. Moreover, in…
Multidimensional data have become ubiquitous and are frequently encountered in situations where the information is aggregated over multiple data atoms. The aggregation can be over time or other features, such as geographical location. We…
Temporal action proposal generation is an important task, akin to object proposals, temporal action proposals are intended to capture "clips" or temporal intervals in videos that are likely to contain an action. Previous methods can be…
Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.…
Temporal object detection has attracted significant attention, but most popular detection methods cannot leverage rich temporal information in videos. Very recently, many algorithms have been developed for video detection task, yet very few…
Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled…