Related papers: Temporal-Enhanced Multimodal Transformer for Refer…
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…
This work proposes an end-to-end multi-camera 3D multi-object tracking (MOT) framework. It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects. Thus, we name it "Past-and-Future reasoning…
Video restoration (e.g., video super-resolution) aims to restore high-quality frames from low-quality frames. Different from single image restoration, video restoration generally requires to utilize temporal information from multiple…
Multi-Object Tracking (MOT) has traditionally focused on a few specific categories, restricting its applicability to real-world scenarios involving diverse objects. Open-Vocabulary Multi-Object Tracking (OVMOT) addresses this by enabling…
Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based algorithms, such as the Kalman Filter, often work well in linear…
Recent advances in reasoning models have shown remarkable progress in text-based domains, but transferring those capabilities to multimodal settings, e.g., to allow reasoning over audio-visual data, still remains a challenge, in part…
Referring video object segmentation (RVOS) is a task that aims to segment the target object in all video frames based on a sentence describing the object. Although existing RVOS methods have achieved significant performance, they depend on…
Modern multi-object tracking (MOT) systems usually model the trajectories by associating per-frame detections. However, when camera motion, fast motion, and occlusion challenges occur, it is difficult to ensure long-range tracking or even…
Current multi-object tracking (MOT) algorithms typically overlook issues inherent in low-quality videos, leading to significant degradation in tracking performance when confronted with real-world image deterioration. Therefore, advancing…
Effectively handling temporal redundancy remains a key challenge in learning video models. Prevailing approaches often treat each set of frames independently, failing to effectively capture the temporal dependencies and redundancies…
Object detection has long been a topic of high interest in computer vision literature. Motivated by the fact that annotating data for the multi-object tracking (MOT) problem is immensely expensive, recent studies have turned their attention…
Multi-camera tracking plays a pivotal role in various real-world applications. While end-to-end methods have gained significant interest in single-camera tracking, multi-camera tracking remains predominantly reliant on heuristic techniques.…
Visual object tracking with RGB and thermal infrared (TIR) spectra available, shorted in RGBT tracking, is a novel and challenging research topic which draws increasing attention nowadays. In this paper, we propose an RGBT tracker which…
Multi-Object Tracking (MOT) remains a vital component of intelligent video analysis, which aims to locate targets and maintain a consistent identity for each target throughout a video sequence. Existing works usually learn a discriminative…
Joint Detection and Embedding (JDE) trackers have demonstrated excellent performance in Multi-Object Tracking (MOT) tasks by incorporating the extraction of appearance features as auxiliary tasks through embedding Re-Identification task…
Multi-object tracking (MOT) in videos remains challenging due to complex object motions and crowded scenes. Recent DETR-based frameworks offer end-to-end solutions but typically process detection and tracking queries jointly within a single…
Existing online multiple object tracking (MOT) algorithms often consist of two subtasks, detection and re-identification (ReID). In order to enhance the inference speed and reduce the complexity, current methods commonly integrate these…
Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS…
We propose a method for multi-object tracking and segmentation based on a novel memory-based mechanism to associate tracklets. The proposed tracker, MeNToS, addresses particularly the long-term data association problem, when objects are not…
In recent years, Deep Learning has been successfully applied to multimodal learning problems, with the aim of learning useful joint representations in data fusion applications. When the available modalities consist of time series data such…