Related papers: Weakly-supervised Representation Learning for Vide…

Automated Human Activity Recognition has long been a problem of great interest in human-centered and ubiquitous computing. In the last years, a plethora of supervised learning algorithms based on deep neural networks has been suggested to…

This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to…

This paper addresses the problem of self-supervised video representation learning from a new perspective -- by video pace prediction. It stems from the observation that human visual system is sensitive to video pace, e.g., slow motion, a…

Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across…

Long video understanding is a complex task that requires both spatial detail and temporal awareness. While Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input, they suffer from information…

Visual prompting has gained popularity as a method for adapting pre-trained models to specific tasks, particularly in the realm of parameter-efficient tuning. However, existing visual prompting techniques often pad the prompt parameters…

Deep neural networks require collecting and annotating large amounts of data to train successfully. In order to alleviate the annotation bottleneck, we propose a novel self-supervised representation learning approach for spatiotemporal…

Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…

The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits their ability to fully…

Face and person recognition have recently achieved remarkable success under challenging scenarios, such as off-pose and cross-spectrum matching. However, long-range recognition systems are often hindered by atmospheric turbulence, leading…

Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these approaches learn representation by discriminating sampled…

This paper provides a review on representation learning for videos. We classify recent spatiotemporal feature learning methods for sequential visual data and compare their pros and cons for general video analysis. Building effective…

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie,…

Supervised learning usually requires a large amount of labelled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that only approximately label some…

Instance-level contrastive learning techniques, which rely on data augmentation and a contrastive loss function, have found great success in the domain of visual representation learning. They are not suitable for exploiting the rich…

The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking). We make the following contributions: (i) we propose to improve the existing…

We present a method for weakly-supervised action localization based on graph convolutions. In order to find and classify video time segments that correspond to relevant action classes, a system must be able to both identify discriminative…

Soft dynamic time warping (SDTW) is a differentiable loss function that allows for training neural networks from weakly aligned data. Typically, SDTW is used to iteratively compute and refine soft alignments that compensate for temporal…

Visual Place Recognition (VPR) aims to retrieve frames from a geotagged database that are located at the same place as the query frame. To improve the robustness of VPR in perceptually aliasing scenarios, sequence-based VPR methods are…

Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed video clip features. These features are extracted from video encoders typically trained for trimmed action…