Related papers: TSMS-SAM2: Multi-scale Temporal Sampling Augmentat…
Semantic Segmentation combines two sub-tasks: the identification of pixel-level image masks and the application of semantic labels to those masks. Recently, so-called Foundation Models have been introduced; general models trained on very…
While the Segment Anything Model (SAM) excels in semantic segmentation for general-purpose images, its performance significantly deteriorates when applied to medical images, primarily attributable to insufficient representation of medical…
Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…
The limited availability of labeled data has driven advancements in semi-supervised learning for medical image segmentation. Modern large-scale models tailored for general segmentation, such as the Segment Anything Model (SAM), have…
Performing a real-time and accurate instrument segmentation from videos is of great significance for improving the performance of robotic-assisted surgery. We identify two important clues for surgical instrument perception, including local…
The Segment Anything Model (SAM), introduced to the computer vision community by Meta in April 2023, is a groundbreaking tool that allows automated segmentation of objects in images based on prompts such as text, clicks, or bounding boxes.…
Inspired by Segment Anything 2, which generalizes segmentation from images to videos, we propose SAM2MOT--a novel segmentation-driven paradigm for multi-object tracking that breaks away from the conventional detection-association framework.…
Tracking and segmenting multiple similar objects with distinct or complex parts in long-term videos is particularly challenging due to the ambiguity in identifying target components and the confusion caused by occlusion, background clutter,…
Segmenting and recognizing diverse object parts is crucial in computer vision and robotics. Despite significant progress in object segmentation, part-level segmentation remains underexplored due to complex boundaries and scarce annotated…
This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal…
Point cloud videos capture dynamic 3D motion while reducing the effects of lighting and viewpoint variations, making them highly effective for recognizing subtle and continuous human actions. Although Selective State Space Models (SSMs)…
Handling occlusion remains a significant challenge for video instance-level tasks like Multiple Object Tracking (MOT) and Video Instance Segmentation (VIS). In this paper, we propose a novel framework, Amodal-Aware Video Instance…
Instructed Visual Segmentation (IVS) tasks require segmenting objects in images or videos based on natural language instructions. While recent multimodal large language models (MLLMs) have achieved strong performance on IVS, their inference…
Video Object Segmentation (VOS) has emerged as an increasingly important problem with availability of larger datasets and more complex and realistic settings, which involve long videos with global motion (e.g, in egocentric settings),…
Video object segmentation (VOS) aims to segment specified target objects throughout a video. Although state-of-the-art methods have achieved impressive performance (e.g., 90+% J&F) on benchmarks such as DAVIS and YouTube-VOS, these datasets…
Vision Transformers (ViTs) have achieved remarkable success across various vision tasks, yet their deployment is often hindered by prohibitive computational costs. While structured weight pruning and token compression have emerged as…
Moving object segmentation based on LiDAR is a crucial and challenging task for autonomous driving and mobile robotics. Most approaches explore spatio-temporal information from LiDAR sequences to predict moving objects in the current frame.…
Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentation techniques, and methods capturing temporal dependency for…
Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications like smart glasses and IoT devices. We introduce PicoSAM2, a lightweight (1.3M parameters, 336M MACs) promptable segmentation model optimized…
Memory-based trackers are video object segmentation methods that form the target model by concatenating recently tracked frames into a memory buffer and localize the target by attending the current image to the buffered frames. While…