Related papers: Sample Less, Learn More: Efficient Action Recognit…

Action recognition is computationally expensive. In this paper, we address the problem of frame selection to improve the accuracy of action recognition. In particular, we show that selecting good frames helps in action recognition…

A primary challenge faced in few-shot action recognition is inadequate video data for training. To address this issue, current methods in this field mainly focus on devising algorithms at the feature level while little attention is paid to…

This paper is a brief report to our submission to the VIPriors Action Recognition Challenge. Action recognition has attracted many researchers attention for its full application, but it is still challenging. In this paper, we study previous…

With the widespread use of installed cameras, video-based monitoring approaches have seized considerable attention for different purposes like assisted living. Temporal redundancy and the sheer size of raw videos are the two most common…

Slow motion videos are becoming increasingly popular, but capturing high-resolution videos at extremely high frame rates requires professional high-speed cameras. To mitigate this problem, current techniques increase the frame rate of…

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…

Video question-answering is a fundamental task in the field of video understanding. Although current vision--language models (VLMs) equipped with Video Transformers have enabled temporal modeling and yielded superior results, they are at…

Existing action recognition methods typically sample a few frames to represent each video to avoid the enormous computation, which often limits the recognition performance. To tackle this problem, we propose Ample and Focal Network (AFNet),…

Although dense local spatial-temporal features with bag-of-features representation achieve state-of-the-art performance for action recognition, the huge feature number and feature size prevent current methods from scaling up to real size…

Recently, 3D convolutional networks yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost of which is very high. In this paper, we propose a fast but effective way…

Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the limited memory. To address this problem, we propose…

Few-shot video object segmentation aims to reduce annotation costs; however, existing methods still require abundant dense frame annotations for training, which are scarce in the medical domain. We investigate an extremely low-data regime…

We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost. Existing approaches focus on modifying the architecture of 2D networks (e.g. by including filters…

We address the problem of anomaly detection in videos. The goal is to identify unusual behaviours automatically by learning exclusively from normal videos. Most existing approaches are usually data-hungry and have limited generalization…

Many deep learning based video compression artifact removal algorithms have been proposed to recover high-quality videos from low-quality compressed videos. Recently, methods were proposed to mine spatiotemporal information via utilizing…

Action segmentation is the task of temporally segmenting every frame of an untrimmed video. Weakly supervised approaches to action segmentation, especially from transcripts have been of considerable interest to the computer vision…

High resolution images can be acquired using a non-regular sampling sensor which consists of an underlying low resolution sensor that is covered with a non-regular sampling mask. The reconstructed high resolution image is then obtained…

In the context of few-shot classification, the goal is to train a classifier using a limited number of samples while maintaining satisfactory performance. However, traditional metric-based methods exhibit certain limitations in achieving…

Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a…

Training an effective video-and-language model intuitively requires multiple frames as model inputs. However, it is unclear whether using multiple frames is beneficial to downstream tasks, and if yes, whether the performance gain is worth…