Related papers: Mining Multi-Modality Spatio-Temporal Cues for Vid…
Visible-infrared person re-identification (ReID) aims to recognize a same person of interest across a network of RGB and IR cameras. Some deep learning (DL) models have directly incorporated both modalities to discriminate persons in a…
Object re-identification (ReID) in large camera networks faces numerous challenges. First, the similar appearances of objects degrade ReID performance, a challenge that needs to be addressed by existing appearance-based ReID methods.…
Estimating the Most Important Person (MIP) in any social event setup is a challenging problem mainly due to contextual complexity and scarcity of labeled data. Moreover, the causality aspects of MIP estimation are quite subjective and…
There is significant progress in recognizing traditional human activities from videos focusing on highly distinctive actions involving discriminative body movements, body-object and/or human-human interactions. Driver's activities are…
Video-based person re-identification aims to match pedestrians from video sequences across non-overlapping camera views. The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video…
We address the problem of highlight detection from a 360 degree video by summarizing it both spatially and temporally. Given a long 360 degree video, we spatially select pleasantly-looking normal field-of-view (NFOV) segments from unlimited…
Vision-language models bridge visual and linguistic understanding and have proven to be powerful for video recognition tasks. Existing approaches primarily rely on parameter-efficient fine-tuning of image-text pre-trained models, yet they…
Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security. Matching persons across disjoint camera views in their video fragments is inherently challenging due to the…
Modeling temporal information for both detection and tracking in a unified framework has been proved a promising solution to video instance segmentation (VIS). However, how to effectively incorporate the temporal information into an online…
This paper introduces a novel approach to person identification using hand images, designed specifically for criminal investigations. The method is particularly valuable in serious crimes such as sexual abuse, where hand images are often…
Temporal action localization is an important and challenging task that aims to locate temporal regions in real-world untrimmed videos where actions occur and recognize their classes. It is widely acknowledged that video context is a…
Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized…
Detection of video shot transition is a crucial pre-processing step in video analysis. Previous studies are restricted on detecting sudden content changes between frames through similarity measurement and multi-scale operations are widely…
Recent advancements in deep learning have significantly enhanced content-based retrieval methods, notably through models like CLIP that map images and texts into a shared embedding space. However, these methods often struggle with…
We propose \textbf{KeyRe-ID}, a keypoint-guided video-based person re-identification framework consisting of global and local branches that leverage human keypoints for enhanced spatiotemporal representation learning. The global branch…
Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabular tasks without task-specific training. However, their effectiveness is constrained by…
In this paper, we address the problem of spatio-temporal person retrieval from multiple videos using a natural language query, in which we output a tube (i.e., a sequence of bounding boxes) which encloses the person described by the query.…
Video-based person re-identification (ReID) is a challenging problem, where some video tracks of people across non-overlapping cameras are available for matching. Feature aggregation from a video track is a key step for video-based person…
Video foreground segmentation (VFS) is an important computer vision task wherein one aims to segment the objects under motion from the background. Most of the current methods are image-based, i.e., rely only on spatial cues while ignoring…
Detecting transitions between intro/credits and main content in videos is a crucial task for content segmentation, indexing, and recommendation systems. Manual annotation of such transitions is labor-intensive and error-prone, while…