20 accepted papers
Visual perception in modern Vision-Language Models (VLM) is constrained by a fundamental perceptual bandwidth bottleneck: a broad field-of-view inevitably sacrifices the fine-grained details necessary for complex reasoning. Inspired by the classical paradigms of active vision and information foragin…
In this paper, we present Chain-of-Models Pre-Training (CoM-PT), a novel performance-lossless training acceleration method for vision foundation models (VFMs). This approach fundamentally differs from existing acceleration methods in its core motivation: rather than optimizing each model individuall
Biomedical reasoning integrates structured, codified knowledge with tacit, experience-driven insights. Depending on the context, quantity, and nature of available evidence, researchers and clinicians use diverse strategies, including rule-based, prototype-based, and case-based reasoning. Effective m…
Visual Entity Linking (VEL) is a crucial task for achieving fine-grained visual understanding, matching objects within images (visual mentions) to entities in a knowledge base. Previous VEL tasks rely on textual inputs, but writing queries for complex scenes can be challenging. Visual inputs like cl…
In this paper, we question if well pre-trained vision transformer (ViT) models could be used as teachers that exhibit scalable properties to advance cross architecture knowledge distillation research, in the context of adopting mainstream large-scale visual recognition datasets for evaluation. To ma…
In recent years, knowledge distillation methods based on contrastive learning have achieved promising results on image classification and object detection tasks. However, in this line of research, we note that less attention is paid to semantic segmentation. Existing methods heavily rely on data aug…
Intent detection, which estimates diverse intents behind user utterances, is an essential component of task-oriented dialogue systems. Previous intent detection models are usually trained offline, which can only handle predefined intent classes. In the real world, new intents may keep challenging de…
Existing feature distillation methods commonly adopt the One-to-one Representation Matching between any pre-selected teacher-student layer pair. In this paper, we present $N$-to-$O$ne $R$epresentation $M$atching (NORM), a new two-stage knowledge distillation method, which relies on a simpleFeature T…
Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches mainly focus on horizontal objects, leaving multi-oriented objects that are common in aerial images unexplored. This p…
Temporal action detection (TAD) is an important yet challenging task in video understanding. It aims to simultaneously predict the semantic label and the temporal interval of every action instance in an untrimmed video. Rather than end-to-end learning, most existing methods adopt a head-only learnin…
Magnetic actuation holds promise for wirelessly controlling small, magnetic surgical tools and may enable the next generation of ultra minimally invasive surgical robotic systems. Precise torque and force exertion are required for safe surgical operations and accurate state control. Dipole field est
Real-time visual localization of needles is necessary for various surgical applications, including surgical automation and visual feedback. In this study we investigate localization and autonomous robotic control of needles in the context of our magneto-suturing system. Our system holds the potentia…
Current developments in temporal event or action localization usually target actions captured by a single camera. However, extensive events or actions in the wild may be captured as a sequence of shots by multiple cameras at different positions. In this paper, we propose a new and challenging task c…
This paper proposes a magnetic needle steering controller to manipulate mesoscale magnetic suture needles for executing planned suturing motion. This is an initial step towards our research objective: enabling autonomous control of magnetic suture needles for suturing tasks in minimally invasive sur…
This paper proposes a generic cleaning module to address lens fogging and soiling problems for insertable robotic cameras in laparoscopic surgery. The proposed lens cleaning module features minimal intraoperative interruption for surgeons to maintain clear visual field. The technical challenges for…
This paper proposes a novel in-vivo robotic laparo-scopic camera design with an optimized illumination system, which is a crucial component for achieving high imaging quality. The robotic camera design with three extendable wings can reserve sufficient on-board space to harbor the optimized illumina…
Robotic systems have recently drawn attention in minimally invasive surgeries due to their increased dexterity feature. A major drawback of these systems is image blurring due to lens contamination which cause imaging impairment during up to 40% of surgery time. This paper demonstrates a novel lapar…
Robotic camera systems have recently drawn attention in minimally invasive surgeries(MIS). Control and manipulation of these systems during traversing abdominal cavity is associated with camera-tissue interaction. This paper demonstrates a theoretical and experimental analysis of a wireless laparosc…
In this paper, we developed a small wheel-legged mobile robot system, which could walk on different road environments using wheels or legs. It is composed of mechanical, sensor and control subsystems. The mechanical subsystem includes a wheel-legged mobile platform, a rigid robotic arm and a flexibl…
This paper presents the design of a novel insertable robotic capsule camera system for single incision laparoscopic surgery. This design features a unified mechanism for anchoring, navigating, and rotating an insertable camera by externally generated rotational magnetic field. The design is inspired…