Related papers: BIT: Bi-Level Temporal Modeling for Efficient Supe…
Video segmentation encompasses a wide range of categories of problem formulation, e.g., object, scene, actor-action and multimodal video segmentation, for delineating task-specific scene components with pixel-level masks. Recently,…
Recent advances in Vision Transformers (ViTs) have significantly advanced semantic segmentation performance. However, their adaptation to new target domains remains challenged by distribution shifts, which often disrupt global attention…
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…
We address the problem of temporal localization of repetitive activities in a video, i.e., the problem of identifying all segments of a video that contain some sort of repetitive or periodic motion. To do so, the proposed method represents…
Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for the spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or…
This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal…
We present a novel approach for unsupervised activity segmentation which uses video frame clustering as a pretext task and simultaneously performs representation learning and online clustering. This is in contrast with prior works where…
Temporal human action detection aims to identify and localize action segments within untrimmed videos, serving as a pivotal task in video understanding. Despite the progress achieved by prior architectures like CNN and Transformer models,…
In this paper, we present an efficient spatial-temporal representation for video person re-identification (reID). Firstly, we propose a Bilateral Complementary Network (BiCnet) for spatial complementarity modeling. Specifically, BiCnet…
Semantic segmentation of motion capture sequences plays a key part in many data-driven motion synthesis frameworks. It is a preprocessing step in which long recordings of motion capture sequences are partitioned into smaller segments.…
Recently, large-scale pre-trained vision-language models (e.g., CLIP), have garnered significant attention thanks to their powerful representative capabilities. This inspires researchers in transferring the knowledge from these large…
Video action recognition has made significant strides, but challenges remain in effectively using both spatial and temporal information. While existing methods often focus on either spatial features (e.g., object appearance) or temporal…
Existing online video segmentation models typically combine a per-frame segmenter with complex specialized tracking modules. While effective, these modules introduce significant architectural complexity and computational overhead. Recent…
Semantic segmentation is a well-addressed topic in the computer vision literature, but the design of fast and accurate video processing networks remains challenging. In addition, to run on embedded hardware, computer vision models often…
Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing…
Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with…
Fine-grained action segmentation in long untrimmed videos is an important task for many applications such as surveillance, robotics, and human-computer interaction. To understand subtle and precise actions within a long time period,…
Long video understanding presents challenges due to the inherent high computational complexity and redundant temporal information. An effective representation for long videos must efficiently process such redundancy while preserving…
Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend…
Video data is with complex temporal dynamics due to various factors such as camera motion, speed variation, and different activities. To effectively capture this diverse motion pattern, this paper presents a new temporal adaptive module…