Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks42 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.
- Prompting for Multi-Modal Tracking215
A novel multi-modal prompt tracker (ProTrack), which can transfer the multi- modal inputs to a single modality by the prompt paradigm, and can achieve high-performance multi- Modal tracking by only altering the inputs, even without any extra training on multi-Modal data.
- 130
- DepthTrack: Unveiling the Power of RGBD Tracking130
A new RGBD tracking dataset - Depth-Track - is introduced that has twice as many sequences and scene types than in the largest existing dataset, and three times more objects, and the average length of the sequences, number of deformable objects and the number of annotated tracking attributes have been increased.
- The Ninth Visual Object Tracking VOT2021 Challenge Results127
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative; results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years.
- 115
- VisDrone-SOT2018: The Vision Meets Drone Single-Object Tracking Challenge Results87
The evaluation protocol of the VisDrone-SOT2018 challenge is presented and the results of a comparison of 22 trackers on the benchmark dataset are presented, which are publicly available on the challenge website.
- Depth-aided Camouflaged Object Detection60
Inspired by research on biology and evolution, depth information is introduced as an additional cue to help break camouflage, which can provide spatial information and texture-free separation for foreground and background.
- 27
- KD-SCFNet: Towards more accurate and lightweight salient object detection via knowledge distillation27
- 25
- 22
- X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs19
X-Former is a lightweight transformer module designed to exploit the complementary strengths of CL and MIM through an innovative interaction mechanism that bootstraps vision-language representation learning and multimodal-to-multimodal generative learning from two frozen vision encoders.
- 17
- 15
- Effect of the Kickstart exoskeleton lower extremity walking system on improving lower extremity walking ability in subacute stroke patients: a randomized controlled trial13
The Kickstart® Walk assist system can increase stroke patients’ lower limb strength and motor function and improve their walking ability and there is a lack of high-quality, randomized controlled trials to validate its effectiveness.
- 10
- 8
- Towards Generic 3D Tracking in RGBD Videos: Benchmark and Baseline7
This paper investigates a novel problem: is it possible to track a generic 3D object in RGBD videos and predict 3D bounding boxes of the object of interest and proposes an effective tracking baseline to estimate 3D bounding boxes for arbitrary objects in RGBD videos, by fusing appearance and spatial information effectively.
- 6
- 5
- 5
- Depth-only Object Tracking5
The end-to-end trained RGBD-DiMP outperforms the recent VOT 2020 RGBD winners and generates depth maps for tracking from the scratch with the generated data and fine-tune it with the available small RGBD tracking datasets.
- Infrared target tracking based on template adaptive Mean Shift4
An algorithm combining improved Mean Shift with incremental Support Vector Machine for infrared target tracking with machine learning theory introduced and incremental support vector machine was used to update target template adaptively, thus target tracking problem was converted to a problem of classification between the target and the background.
- 3
- 3
- Multi-branch feature fusion and refinement network for salient object detection3
A multi-branch feature fusion and refinement network (MFFRNet) is proposed, which is a framework for treating low-level features and high-level features differently, and effectively fuses the information of multi-level features to make the results more accurate.
- 1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation2
This technical report investigated and validated the effectiveness of static-dominant data and frame sampling on this challenging setting and achieves a J&F score of 0.5447 in the competition phase and ranks 1st in the MeViS track of the PVUW Challenge.
- 2
- 2
- 2
- 2
- Leveraging Geometric Priors for Unaligned Scene Change Detection1
This work introduces geometric priors for the first time to address the core challenges of unaligned SCD, for reliable identification of visual overlaps, robust correspondence establishment, and explicit occlusion detection.
- Contextual feature fusion and refinement network for camouflaged object detection1
A multiple-receptive-fields-based feature extraction module (MFM) that obtains features from multiple scales of receptive fields that establishes the information flow between adjacent layers through an attention mechanism and is validated as an effective COD model on four benchmark datasets.
- D2Net: discriminative feature extraction and details preservation network for salient object detection1
Comparisons with 17 existing state-of-the-art SOD methods on five popular datasets demonstrate the superiority of the proposed D2Net, and the effectiveness of each proposed module is verified through numerous ablation experiments.
- An improved moving object tracking algorithm based on CAMSHIFT1
An improved moving object tracking algorithm which combined Kalman filter predictor with Camshift algorithm can effectively reduce the tracking error accumulation in the tracking process, greatly reduce the template drift, shorten the tracking time, and can have a better practicability and real-time performance.
- A Saliency-Based Object Tracking Method for UAV Application1
A new compounded feature to track the object by combining saliency feature and color features for the conspicuousness of the objects in the videos captured by UAVs is proposed, using a spectrum-based saliency detection method - quaternion type-II DCT image signatures.
- –
- Prostate Cancer Diagnosis Using an Explainable Credibility Estimation Network Incorporating a Rejection Mechanism–
This study equips clinical practitioners with the ability to comprehend the decision-making process of the CAD system and manage the output results through an intuitive display, which enhances diagnostic accuracy, potentially impacting clinicians' decision-making and patient outcomes.
- –
- –
- –
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.