Related papers: Turbulence-Robust Dynamic Object Segmentation with…

We report on the application of a high-capacity semantic segmentation pipeline to the GOOSE 2D Semantic Segmentation Challenge for unstructured off-road environments. Using a FlashInternImage-B backbone together with a UPerNet decoder, we…

Video Object Segmentation (VOS) is foundational to numerous computer vision applications, including surveillance, autonomous driving, robotics and generative video editing. However, existing VOS models often struggle with precise mask…

Atmospheric turbulence poses a challenge for the interpretation and visual perception of visual imagery due to its distortion effects. Model-based approaches have been used to address this, but such methods often suffer from artefacts…

Precise instrument segmentation aid surgeons to navigate the body more easily and increase patient safety. While accurate tracking of surgical instruments in real-time plays a crucial role in minimally invasive computer-assisted surgeries,…

Semi-supervised remote sensing (RS) image semantic segmentation offers a promising solution to alleviate the burden of exhaustive annotation, yet it fundamentally struggles with pseudo-label drift, a phenomenon where confirmation bias leads…

Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challenges such as action variability, ambiguous boundaries, and high annotation costs remain,…

Training-free Camouflaged Object Segmentation (COS) seeks to segment camouflaged objects without task-specific training, by automatically generating visual prompts to guide the Segment Anything Model (SAM). However, existing pipelines…

In this work, we propose a novel Reversible Recursive Instance-level Object Segmentation (R2-IOS) framework to address the challenging instance-level object segmentation task. R2-IOS consists of a reversible proposal refinement sub-network…

Referring Remote Sensing Image Segmentation (RRSIS) aims to segment target objects in remote sensing (RS) images based on textual descriptions. Although Segment Anything Model 2 (SAM2) has shown remarkable performance in various…

This technical report presents the 1st winning model for UG2+, a task in CVPR 2024 UAV Tracking and Pose-Estimation Challenge. This challenge faces difficulties in drone detection, UAV-type classification and 2D/3D trajectory estimation in…

High-resolution spatiotemporal simulations effectively capture the complexities of atmospheric plume dispersion in complex terrain. However, their high computational cost makes them impractical for applications requiring rapid responses or…

Variational inequalities play a pivotal role in a wide array of scientific and engineering applications. This project presents two techniques for adaptive mesh refinement (AMR) in the context of variational inequalities, with a specific…

Integrating information from multiple modalities enhances the robustness of scene perception systems in autonomous vehicles, providing a more comprehensive and reliable sensory framework. However, the modality incompleteness in multi-modal…

Time-Series (TS) exhibits pronounced non-stationarity. Consequently, most forecasting methods display compromised robustness to concept drift, despite the prevalent application of instance normalization. We tackle this challenge by first…

Amodal object segmentation is a challenging task that involves segmenting both visible and occluded parts of an object. In this paper, we propose a novel approach, called Coarse-to-Fine Segmentation (C2F-Seg), that addresses this problem by…

Foundation models achieve state-of-the-art performance across different tasks, but their size and computational demands raise concerns about accessibility and sustainability. Existing efficiency methods often require additional retraining…

Diffusion-based image super-resolution (SR) methods have demonstrated remarkable performance. Recent advancements have introduced deterministic sampling processes that reduce inference from 15 iterative steps to a single step, thereby…

Motion Expression guided Video Segmentation is a challenging task that aims at segmenting objects in the video based on natural language expressions with motion descriptions. Unlike the previous referring video object segmentation (RVOS),…

Multi-object tracking (MOT) is a fundamental task in computer vision with critical applications in autonomous driving and robotics. Multimodal MOT that integrates visible light and thermal infrared information is particularly essential for…

Accurate tumor segmentation and classification in breast ultrasound (BUS) imaging remain challenging due to low contrast, speckle noise, and diverse lesion morphology. This study presents a multi-task deep learning framework that jointly…