Related papers: A Hybrid Attention Mechanism for Weakly-Supervised…
Recently, substantial research effort has focused on how to apply CNNs or RNNs to better extract temporal patterns from videos, so as to improve the accuracy of video classification. In this paper, however, we show that temporal…
Spatio-temporal contexts are crucial in understanding human actions in videos. Recent state-of-the-art Convolutional Neural Network (ConvNet) based action recognition systems frequently involve 3D spatio-temporal ConvNet filters, chunking…
Video moment retrieval is to identify the target moment according to the given sentence in an untrimmed video. Due to temporal boundary annotations of the video are extremely time-consuming to acquire, modeling in the weakly-supervised…
Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g.,…
The temporal action segmentation task segments videos temporally and predicts action labels for all frames. Fully supervising such a segmentation model requires dense frame-wise action annotations, which are expensive and tedious to…
Weakly-supervised Temporal Action Localization (W-TAL) aims to classify and localize all action instances in an untrimmed video under only video-level supervision. However, without frame-level annotations, it is challenging for W-TAL…
Few-shot learning (FSL) aims to learn novel visual categories from very few samples, which is a challenging problem in real-world applications. Many methods of few-shot classification work well on general images to learn global…
Video activity localisation has recently attained increasing attention due to its practical values in automatically localising the most salient visual segments corresponding to their language descriptions (sentences) from untrimmed and…
This paper presents the first-rank solution for the Multi-Modal Action Recognition Challenge, part of the Multi-Modal Visual Pattern Recognition Workshop at the \acl{ICPR} 2024. The competition aimed to recognize human actions using a…
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…
We propose action-agnostic point-level (AAPL) supervision for temporal action detection to achieve accurate action instance detection with a lightly annotated dataset. In the proposed scheme, a small portion of video frames is sampled in an…
Fitness movement recognition, a focused subdomain of human activity recognition (HAR), plays a vital role in health monitoring, rehabilitation, and personalized fitness training by enabling automated exercise classification from video data.…
As of today, state-of-the-art activity recognition from wearable sensors relies on algorithms being trained to classify fixed windows of data. In contrast, video-based Human Activity Recognition, known as Temporal Action Localization (TAL),…
Spatial and temporal modeling is one of the most core aspects of few-shot action recognition. Most previous works mainly focus on long-term temporal relation modeling based on high-level spatial representations, without considering the…
In this paper, we propose a novel hand-based person recognition method for the purpose of criminal investigations since the hand image is often the only available information in cases of serious crime such as sexual abuse. Our proposed…
Recent advances in single-frame object detection and segmentation techniques have motivated a wide range of works to extend these methods to process video streams. In this paper, we explore the idea of hard attention aimed for…
Weakly supervised violence detection refers to the technique of training models to identify violent segments in videos using only video-level labels. Among these approaches, multimodal violence detection, which integrates modalities such as…
Current state-of-the-art approaches for spatio-temporal action detection have achieved impressive results but remain unsatisfactory for temporal extent detection. The main reason comes from that, there are some ambiguous states similar to…
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process. However, traditional methods of human activity recognition require a large amount of such strictly labeled data for…
It is challenging for artificial intelligence systems to achieve accurate video recognition under the scenario of low computation costs. Adaptive inference based efficient video recognition methods typically preview videos and focus on…