Related papers: CrossTracker: Robust Multi-modal 3D Multi-Object T…

Fusing data from cameras and LiDAR sensors is an essential technique to achieve robust 3D object detection. One key challenge in camera-LiDAR fusion involves mitigating the large domain gap between the two sensors in terms of coordinates…

Mobile monocular 3D object detection (Mono3D) (e.g., on a vehicle, a drone, or a robot) is an important yet challenging task. Existing transformer-based offline Mono3D models adopt grid-based vision tokens, which is suboptimal when using…

In this paper, we focus on the multi-object tracking (MOT) problem of automatic driving and robot navigation. Most existing MOT methods track multiple objects using a singular RGB camera, which are prone to camera field-of-view and suffer…

Point clouds and RGB images are naturally complementary modalities for 3D visual understanding - the former provides sparse but accurate locations of points on objects, while the latter contains dense color and texture information. Despite…

Multi-object tracking (MOT) endeavors to precisely estimate the positions and identities of multiple objects over time. The prevailing approach, tracking-by-detection (TbD), first detects objects and then links detections, resulting in a…

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…

Multi-modal fusion has emerged as a promising paradigm for accurate 3D object detection. However, performance degrades substantially when deployed in target domains different from training. In this work, focusing on dual-branch…

Online Multiple Target Tracking (MTT) is often addressed within the tracking-by-detection paradigm. Detections are previously extracted independently in each frame and then objects trajectories are built by maximizing specifically designed…

Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent identities across frames. However, most existing approaches primarily rely on…

Multi-object tracking (MOT) is one of the most challenging tasks in computer vision, where it is important to correctly detect objects and associate these detections across frames. Current approaches mainly focus on tracking objects in each…

3D perception in LiDAR point clouds is crucial for a self-driving vehicle to properly act in 3D environment. However, manually labeling point clouds is hard and costly. There has been a growing interest in self-supervised pre-training of 3D…

Infrared-visible object detection aims to achieve robust object detection by leveraging the complementary information of infrared and visible image pairs. However, the commonly existing modality misalignment problem presents two challenges:…

3D LiDAR-based single object tracking (SOT) relies on sparse and irregular point clouds, posing challenges from geometric variations in scale, motion patterns, and structural complexity across object categories. Current category-specific…

Decoder-only methods, such as GPT, have demonstrated superior performance in many areas compared to traditional encoder-decoder structure transformer methods. Over the years, end-to-end methods based on the traditional transformer…

Multiple object tracking (MOT) is a task in computer vision that aims to detect the position of various objects in videos and to associate them to a unique identity. We propose an approach based on Constraint Programming (CP) whose goal is…

Advances in sensing and learning algorithms have led to increasingly mature solutions for human detection by robots, particularly in selected use-cases such as pedestrian detection for self-driving cars or close-range person detection in…

Object tracking is divided into single-object tracking (SOT) and multi-object tracking (MOT). MOT aims to maintain the identities of multiple objects across a series of continuous video sequences. In recent years, MOT has made rapid…

Cross-modal retrieval aims to learn discriminative and modal-invariant features for data from different modalities. Unlike the existing methods which usually learn from the features extracted by offline networks, in this paper, we propose…

Maintaining robust 3D perception under dynamic and unpredictable test-time conditions remains a critical challenge for autonomous driving systems. Existing test-time adaptation (TTA) methods often fail in high-variance tasks like 3D object…

We introduce CoTracker, a transformer-based model that tracks a large number of 2D points in long video sequences. Differently from most existing approaches that track points independently, CoTracker tracks them jointly, accounting for…