Computer Vision

The paper presents SenseNova-Vision, a unified multimodal model for computer vision tasks using natural language instructions and optional visual prompts, trained primarily on a new corpus and requiri…

This study systematically evaluates Vision Mamba models for detecting AI-generated images, finding that while they show promise, their current strengths and limitations must be understood relative to…

The paper introduces PIXIE, a zero-shot framework for estimating 6D pose of an object from an RGB image using only an untextured 3D model.

This paper identifies and explores a new type of physical adversarial attack on vision systems called Scratch-induced Lens Adversarial Streak Hijacking (SLASH), which causes persistent and selective o…

This paper investigates acoustic attacks on Artificial Intelligence (AI) based computer vision systems using lower frequencies in the audible range, and explores the impact on various image and object…

This paper proposes DPNeXt, a streamlined multi-scale feature fusion decoder for Multi-Task Learning (MTL) in robotics perception systems, improving frozen VFM utilization and mitigating negative indu…

The paper introduces Instruct-Particulate, a model that predicts kinematic part segmentation and joint motion parameters for articulated 3D objects from a 3D mesh and a target kinematic specification.

The paper shows that using random cropping, a standard data augmentation technique, can naturally amplify differential privacy guarantees for machine learning models without requiring any changes to t…

Places in the Wild introduces a massive, high-resolution RAW photograph dataset of 67,574 images captured in situ across 810 locations, providing unprecedented detail for ecologically valid vision res…

This paper presents a non-contact length estimation framework for commercial greenhouse cucumbers using a RGB-D camera.

This study empirically benchmarks classical and quantum machine learning models for image recognition, finding that while quantum models offer superior accuracy and resource efficiency at high dimensi…

This paper presents a traffic sign recognition system using YOLOv2 with two modifications to improve efficiency and accuracy.

This paper introduces a method to train visually grounded vision-language models for radiology without manual spatial annotations.

The paper introduces ProxyPose, a method for six-degree-of-freedom (6-DoF) pose tracking using a video diffusion model and a single marked pixel in the first frame.

This paper presents OneCanvas, a method for 3D scene understanding in Vision-Language Models that aggregates patch features onto a single panoramic canvas.

The paper introduces Multi-temporal Referring Segmentation (MTRS), a new task requiring models to segment language-described temporal changes, and proposes MTRefSeg-R1, a specialized framework that ac…

This paper presents an open-source computer vision pipeline for classifying vehicle body types from naturalistic roadway video.

The paper introduces CAIAMAR, a multi-agent reasoning framework that achieves context-aware and high-fidelity anonymization of personally identifiable information (PII) in street imagery, significantl…

A new deep learning method, Mamba Transformer, is proposed for accurate single-shot 3D reconstruction from a single high frequency fringe image.

The paper reframes industrial visual sim-to-real transfer as a domain-gap problem categorized by the availability of explicit object geometry (CAD), arguing that the required prior evidence dictates t…