Related papers: From Pairs to Sequences: Track-Aware Policy Gradie…

Current best local descriptors are learned on a large dataset of matching and non-matching keypoint pairs. However, data of this kind is not always available since detailed keypoint correspondences can be hard to establish. On the other…

Object tracking is an essential problem in computer vision that has been researched for several decades. One of the main challenges in tracking is to adapt to object appearance changes over time and avoiding drifting to background clutter.…

Previous part-based attribute recognition approaches perform part detection and attribute recognition in separate steps. The parts are not optimized for attribute recognition and therefore could be sub-optimal. We present an end-to-end deep…

Learning from Demonstration (LfD) is a promising approach to enable Multi-Robot Systems (MRS) to acquire complex skills and behaviors. However, the intricate interactions and coordination challenges in MRS pose significant hurdles for…

We propose a deep video prediction model conditioned on a single image and an action class. To generate future frames, we first detect keypoints of a moving object and predict future motion as a sequence of keypoints. The input image is…

The field of multi-object tracking has recently seen a renewed interest in the good old schema of tracking-by-detection, as its simplicity and strong priors spare it from the complex design and painful babysitting of tracking-by-attention…

Real-time 3D object detection from point clouds is essential for dynamic scene understanding in applications such as augmented reality, robotics and navigation. We introduce a novel Spatial-prioritized and Rank-aware 3D object detection…

We propose a novel recurrent attentional structure to localize and recognize objects jointly. The network can learn to extract a sequence of local observations with detailed appearance and rough context, instead of sliding windows or…

Referring 3D Gaussian Splatting (R3DGS), which utilizes natural language for 3D object segmentation, has emerged as a crucial capability for embodied AI. However, existing methods typically rely on expensive per-scene manual annotation and…

Tracking by detection, the dominant approach for online multi-object tracking, alternates between localization and association steps. As a result, it strongly depends on the quality of instantaneous observations, often failing when objects…

Many query-based approaches for 3D Multi-Object Tracking (MOT) adopt the tracking-by-attention paradigm, utilizing track queries for identity-consistent detection and object queries for identity-agnostic track spawning.…

In recent years, deep learning based visual tracking methods have obtained great success owing to the powerful feature representation ability of Convolutional Neural Networks (CNNs). Among these methods, classification-based tracking…

Existing object proposal algorithms usually search for possible object regions over multiple locations and scales separately, which ignore the interdependency among different objects and deviate from the human perception procedure. To…

The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to…

This work presents WorldCompass, a novel Reinforcement Learning (RL) post-training framework for the long-horizon, interactive video-based world models, enabling them to explore the world more accurately and consistently based on…

Visual pedestrian tracking represents a promising research field, with extensive applications in intelligent surveillance, behavior analysis, and human-computer interaction. However, real-world applications face significant occlusion…

Lane detection is to determine the precise location and shape of lanes on the road. Despite efforts made by current methods, it remains a challenging task due to the complexity of real-world scenarios. Existing approaches, whether…

Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no benchmark exists to evaluate these capabilities holistically. To bridge this gap, we…

With the immense growth of dataset sizes and computing resources in recent years, so-called foundation models have become popular in NLP and vision tasks. In this work, we propose to explore foundation models for the task of keypoint…

Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry (VO) and simultaneous localization and mapping (SLAM), where classic methods consisting of hand-crafted features and sampling-based outlier…