Related papers: V$^{2}$-SAM: Marrying SAM2 with Multi-Prompt Exper…

Task-oriented communication presents a promising approach to improve the communication efficiency of edge inference systems by optimizing learning-based modules to extract and transmit relevant task information. However, real-time…

360 video object segmentation (360VOS) aims to predict temporally-consistent masks in 360 videos, offering full-scene coverage, benefiting applications, such as VR/AR and embodied AI. Learning 360VOS model is nontrivial due to the lack of…

Although new vision foundation models such as Segment Anything Model 2 (SAM2) have significantly enhanced zero-shot image segmentation capabilities, reliance on human-provided prompts poses significant challenges in adapting SAM2 to medical…

We propose a novel approach for disentangling visual and semantic features from the backbones of pre-trained diffusion models, enabling visual correspondence in a manner analogous to the well-established semantic correspondence. While…

We introduce Grounded SAM, which uses Grounding DINO as an open-set object detector to combine with the segment anything model (SAM). This integration enables the detection and segmentation of any regions based on arbitrary text inputs and…

Vehicle-to-everything (V2X) cooperation has emerged as a promising paradigm to overcome the perception limitations of classical autonomous driving by leveraging information from both ego-vehicle and infrastructure sensors. However,…

Visual Object Tracking (VOT) is widely used in applications like autonomous driving to continuously track targets in videos. Existing methods can be roughly categorized into template matching and autoregressive methods, where the former…

Segment Anything Model (SAM) represents a large-scale segmentation model that enables powerful zero-shot capabilities with flexible prompts. While SAM can segment any object in zero-shot, it requires user-provided prompts for each target…

Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for applications in embodied AI and remote collaboration. This task is exceptionally difficult…

The Segment Anything Model (SAM) has gained significant attention for its impressive performance in image segmentation. However, it lacks proficiency in referring video object segmentation (RVOS) due to the need for precise user-interactive…

Recent studies reveal the vulnerability of the image segmentation foundation model SAM to adversarial examples. Its successor, SAM2, has attracted significant attention due to its strong generalization capability in video segmentation.…

As large-scale foundation models trained on billions of image--mask pairs covering a vast diversity of scenes, objects, and contexts, SAM and its upgraded version, SAM~2, have significantly influenced multiple fields within computer vision.…

Interactive Medical-SAM2 GUI is an open-source desktop application for semi-automatic annotation of 2D and 3D medical images. Built on the Napari multi-dimensional viewer, box/point prompting is integrated with SAM2-style propagation by…

We present V$^2$Dial - a novel expert-based model specifically geared towards simultaneously handling image and video input data for multimodal conversational tasks. Current multimodal models primarily focus on simpler tasks (e.g., VQA,…

In this paper, we propose an Audio-Language-Referenced SAM 2 (AL-Ref-SAM 2) pipeline to explore the training-free paradigm for audio and language-referenced video object segmentation, namely AVS and RVOS tasks. The intuitive solution…

Error detection is crucial in industrial training, healthcare, and assembly quality control. Most existing work assumes a single-view setting and cannot handle the practical case where a third-person (exo) demonstration is used to assess a…

Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…

Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. Existing vision-language approaches address this limitation…

The egocentric and exocentric viewpoints of a human activity look dramatically different, yet invariant representations to link them are essential for many potential applications in robotics and augmented reality. Prior work is limited to…

Cross-view object Geo-localization aims to precisely pinpoint the same object across large-scale satellite imagery based on drone images. Due to significant differences in viewpoint and scale, coupled with complex background interference,…