Related papers: Domain Adaptive Video Segmentation via Temporal Ps…
Continual Test-Time Adaptation (CTTA) enables pre-trained models to adapt to continuously evolving domains. Existing methods have improved robustness but typically rely on fixed or batch-level thresholds, which cannot account for varying…
Unsupervised domain adaptation aims to transfer knowledge from a source domain to a target domain so that the target domain data can be recognized without any explicit labelling information for this domain. One limitation of the problem…
Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…
Skeleton-based temporal action segmentation is a fundamental yet challenging task, playing a crucial role in enabling intelligent systems to perceive and respond to human activities. While fully-supervised methods achieve satisfactory…
Temporal segmentation of long videos is an important problem, that has largely been tackled through supervised learning, often requiring large amounts of annotated training data. In this paper, we tackle the problem of self-supervised…
In low-level video analyses, effective representations are important to derive the correspondences between video frames. These representations have been learned in a self-supervised fashion from unlabeled images or videos, using carefully…
For a robot deployed in the world, it is desirable to have the ability of autonomous learning to improve its initial pre-set knowledge. We formalize this as a bootstrapped self-supervised learning problem where a system is initially…
Video segmentation aims at partitioning video sequences into meaningful segments based on objects or regions of interest within frames. Current video segmentation models are often derived from image segmentation techniques, which struggle…
Stereo matching in minimally invasive surgery (MIS) is essential for next-generation navigation and augmented reality. Yet, dense disparity supervision is nearly impossible due to anatomical constraints, typically limiting annotations to…
In this paper, we investigate the problem of unpaired video-to-video translation. Given a video in the source domain, we aim to learn the conditional distribution of the corresponding video in the target domain, without seeing any pairs of…
This paper strives for spatio-temporal localization of human actions in videos. In the literature, the consensus is to achieve localization by training on bounding box annotations provided for each frame of each training video. As…
While most modern video understanding models operate on short-range clips, real-world videos are often several minutes long with semantically consistent segments of variable length. A common approach to process long videos is applying a…
Video object segmentation is challenging due to the factors like rapidly fast motion, cluttered backgrounds, arbitrary object appearance variation and shape deformation. Most existing methods only explore appearance information between two…
Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene…
Unsupervised Domain Adaptation (UDA) aims to classify unlabeled target domain by transferring knowledge from labeled source domain with domain shift. Most of the existing UDA methods try to mitigate the adverse impact induced by the shift…
Temporal cues in videos provide important information for recognizing actions accurately. However, temporal-discriminative features can hardly be extracted without using an annotated large-scale video action dataset for training. This paper…
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…
Temporal sentence grounding in videos (TSGV) faces challenges due to public TSGV datasets containing significant temporal biases, which are attributed to the uneven temporal distributions of target moments. Existing methods generate…
Unsupervised domain adaptation (UDA) has become increasingly prevalent in scene text recognition (STR), especially where training and testing data reside in different domains. The efficacy of existing UDA approaches tends to degrade when…
Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a…