Related papers: Spatial-Temporal Graph Enhanced DETR Towards Multi…

Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention…

Skeleton-based Human Activity Recognition has achieved great interest in recent years as skeleton data has demonstrated being robust to illumination changes, body scales, dynamic camera views, and complex background. In particular,…

One-shot transfer of dexterous grasps to novel scenes with object and context variations has been a challenging problem. While distilled feature fields from large vision models have enabled semantic correspondences across 3D scenes, their…

Federated real-time object detection using transformers in Intelligent Transportation Systems (ITS) faces three major challenges: (1) missing-class non-IID data heterogeneity from geographically diverse traffic environments, (2) latency…

Most existing video moment retrieval methods rely on temporal sequences of frame- or clip-level features that primarily encode global visual and semantic information. However, such representations often fail to capture fine-grained object…

The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video. While vision Transformers have driven the recent advances in video…

Recently, Transformer-based methods, which predict polygon points or Bezier curve control points for localizing texts, are popular in scene text detection. However, these methods built upon detection transformer framework might achieve…

Object detection in Unmanned Aerial Vehicle (UAV) imagery is fundamentally challenged by a prevalence of small, densely packed, and occluded objects within cluttered backgrounds. Conventional detectors struggle with this domain, as they…

We present a new model named Stacked-DETR(SDETR), which inherits the main ideas in canonical DETR. We improve DETR in two directions: simplifying the cost of training and introducing the stacked architecture to enhance the performance. To…

Traffic prediction is critical for optimizing travel scheduling and enhancing public safety, yet the complex spatial and temporal dynamics within traffic data present significant challenges for accurate forecasting. In this paper, we…

The Transformer-based detectors (i.e., DETR) have demonstrated impressive performance on end-to-end object detection. However, transferring DETR to different data distributions may lead to a significant performance degradation. Existing…

Open world object detection aims at detecting objects that are absent in the object classes of the training data as unknown objects without explicit supervision. Furthermore, the exact classes of the unknown objects must be identified…

This paper addresses the task of segmenting class-agnostic objects in semi-supervised setting. Although previous detection based methods achieve relatively good performance, these approaches extract the best proposal by a greedy strategy,…

Sound event detection (SED) has gained increasing attention with its wide application in surveillance, video indexing, etc. Existing models in SED mainly generate frame-level prediction, converting it into a sequence multi-label…

Effective and Efficient spatio-temporal modeling is essential for action recognition. Existing methods suffer from the trade-off between model performance and model complexity. In this paper, we present a novel Spatio-Temporal Hybrid…

Existing LiDAR-based 3D object detectors usually focus on the single-frame detection, while ignoring the spatiotemporal information in consecutive point cloud frames. In this paper, we propose an end-to-end online 3D video object detector…

Hyperspectral target detection (HTD) aims to identify specific materials based on spectral information in hyperspectral imagery and can detect extremely small-sized objects, some of which occupy a smaller than one-pixel area. However,…

Single-source domain generalization (SDG) in object detection aims to develop a detector using only source domain data that generalizes well to unseen target domains. Existing methods are primarily CNN-based and improve robustness through…

Real-time object detection is crucial for real-world applications as it requires high accuracy with low latency. While Detection Transformers (DETR) have demonstrated significant performance improvements, current real-time DETR models are…

Street scene change detection continues to capture researchers' interests in the computer vision community. It aims to identify the changed regions of the paired street-view images captured at different times. The state-of-the-art network…