Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks75 from public data
- The Eighth Visual Object Tracking VOT2020 Challenge Results350
A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in theVDT challenges.
- 130
- 35
- Visual Jigsaw Post-Training Improves MLLMs25
This work introduces Visual Jigsaw, a generic self-supervised post-training framework designed to strengthen visual understanding in MLLMs that naturally aligns with reinforcement learning from verifiable rewards (RLVR), requires no additional visual generative components, and derives its supervisory signal automatically without any annotations.
- 23
- 22
- 19
- 15
- 15
- 13
- 12
- 11
- 10
- Infrared Small Target Detection Based on Entropy Variation Weighted Local Contrast Measure9
A target saliency enhancement method based on a family of generalized Gaussian functions is introduced, which accurately characterizes the grayscale distribution states of various targets in infrared images and a novel adaptive weighting strategy based on local joint entropy variation characteristics is suggested.
- 8
- Zero-Shot 4D Lidar Panoptic Segmentation7
This work proposes SAL-4D (Segment Anything in Lidar- 4D), a method that utilizes multi-modal robotic sensor setups as a bridge to distill recent developments in Video Object Segmentation in conjunction with off-the-shelf Vision-Language foundation models to Lidar.
- 6
- UWB-INS Fusion Positioning Based on a Two-Stage Optimization Algorithm5
A two-stage fusion localization algorithm achieves a great improvement on positioning system, it can improve the localization accuracy by 79.8% in the NLOS environment and by 36% in the (line-of-sight) LOS environment.
- 5
- Bearing Fault Diagnosis via Graph Autoencoder Networks with Multi-kernel Subdomain Adversarial Domain Adaptation4
This paper proposes multi-kernel subdomain adversarial domain adaptation for graph autoencoder networks (MSADAGAE) to solve the problems of bearing fault diagnosis under variable operating conditions and optimization of feature classification boundaries.
- Runtime Analysis of Stochastic Gradient Descent4
This paper explains how to approximate SGD by stochastic differential equations (SDE) by means of the theoretical foundation of mean first passage time (MFPT), which is then used to determine the runtime of SGD.
- Running-time analysis of evolutionary programming based on Lebesgue measure of searching space4
An analysis of the running time of two EP algorithms based on Gaussian and Cauchy mutations, using an absorbing Markov process model, shows that the upper bounds are impacted by individual number, problem dimension number, searching range, and the Lebesgue measure of the optimal neighborhood.
- 3
- 3
- Duplicate-sensitivity guided transformation synthesis for DBMS correctness bug detection3
This paper introduces duplicate-sensitivity guided transformation synthesis which automatically finds new transformations by first synthesizing many candidates then filtering the nonequivalent ones, and achieves automated synthesis by mutating a query while keeping its duplicate sensitivity, which is a necessary condition for query equivalence.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.