Related papers: Zero-Shot Object Re-Identification in Egocentric K…

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.…

Video Scene Graph Generation (VidSGG) is an important topic in understanding dynamic kitchen environments. Current models for VidSGG require extensive training to produce scene graphs. Recently, Vision Language Models (VLM) and Vision…

Tracklet quality is often treated as an afterthought in most person re-identification (ReID) methods, with the majority of research presenting architectural modifications to foundational models. Such approaches neglect an important…

Accurate surgical instrument segmentation in endoscopy is crucial for computer-assisted interventions, yet remains challenging due to frequent occlusions, rapid motion, and long-term instrument re-entry. While SAM3 provides a powerful…

We introduce SAM3D, a new approach to semi-automatic zero-shot segmentation of 3D images building on the existing Segment Anything Model. We achieve fast and accurate segmentations in 3D images with a four-step strategy involving: user…

Room reidentification (ReID) is a challenging yet essential task with numerous applications in fields such as augmented reality (AR) and homecare robotics. Existing visual place recognition (VPR) methods, which typically rely on global…

We introduce EgoPoints, a benchmark for point tracking in egocentric videos. We annotate 4.7K challenging tracks in egocentric sequences. Compared to the popular TAP-Vid-DAVIS evaluation benchmark, we include 9x more points that go…

Egocentric videos present unique challenges for 3D scene understanding due to rapid camera motion, frequent object occlusions, and limited object visibility. This paper introduces a novel approach to instance segmentation and tracking in…

Object re-identification (ReID) is a key application of city-scale cameras. While classic ReID tasks are often considered as image retrieval, we treat them as spatiotemporal queries for locations and times in which the target object…

We introduce the task of Reconstructing Objects along Hand Interaction Timelines (ROHIT). We first define the Hand Interaction Timeline (HIT) from a rigid object's perspective. In a HIT, an object is first static relative to the scene, then…

Person re-identification (ReID) models are known to suffer from camera bias, where learned representations cluster according to camera viewpoints rather than identity, leading to significant performance degradation under (inter-camera)…

Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are…

Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize language-image…

Video recognition models are typically trained on fixed taxonomies which are often too coarse, collapsing distinctions in object, manner or outcome under a single label. As tasks and definitions evolve, such models cannot accommodate…

In this report, we describe our approach to egocentric video object segmentation. Our method combines large-scale visual pretraining from SAM2 with depth-based geometric cues to handle complex scenes and long-term tracking. By integrating…

Given a target image as query, person re-identification systems retrieve a ranked list of candidate matches on a per-camera basis. In deployed systems, a human operator scans these lists and labels sighted targets by touch or mouse-based…

In recent years, the field of autonomous driving has witnessed remarkable advancements, driven by the integration of a multitude of sensors, including cameras and LiDAR systems, in different prototypes. However, with the proliferation of…

Foundation models like CLIP (Contrastive Language-Image Pretraining) have revolutionized vision-language tasks by enabling zero-shot and few-shot learning through cross-modal alignment. However, their computational complexity and large…

We propose a new setting for detecting unseen objects called Zero-shot Annotation object Detection (ZAD). It expands the zero-shot object detection setting by allowing the novel objects to exist in the training images and restricts the…

We propose a novel feature re-identification method for real-time visual-inertial SLAM. The front-end module of the state-of-the-art visual-inertial SLAM methods (e.g. visual feature extraction and matching schemes) relies on feature tracks…