Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks105 from public data
- LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking1,655
LaSOT is presented, a high-quality benchmark for Large-scale Single Object Tracking that consists of 1,400 sequences with more than 3.5M frames in total, and is the largest, to the best of the authors' knowledge, densely annotated tracking benchmark.
- The Sixth Visual Object Tracking VOT2018 Challenge Results804
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative; results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years.
- 542
- Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking458
A multi-stage tracking framework, Siamese Cascaded RPN (C-RPN), which consists of a sequence of RPNs cascaded from deep high-level to shallow low-level layers in aSiamese network, which achieves state-of-the-art results and runs in real-time.
- Clustered Object Detection in Aerial Images437
This paper proposes a Clustered Detection (ClusDet) network that unifies object clustering and detection in an end-to-end framework and achieves promising performance in comparison with state-of-the-art detectors.
- 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.
- Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking329
In the extensive experiments on popular benchmarks including OTB2013, OTB2015, TC128 and UAV20L, PTAV achieves the best tracking accuracy among all real-time trackers, and in fact performs even better than many deep learning based solutions.
- VisDrone-DET2020: The Vision Meets Drone Object Detection in Image Challenge Results259
Based on the selected 29 robust detection methods, the experimental results comprehensively are discussed, which shows the effectiveness of ensemble learning and data augmentation in drone captured object detection.
- SANet: Structure-Aware Network for Visual Tracking256
This work utilizes recurrent neural network (RNN) to model object structure, and incorporates it into CNN to improve its robustness to similar distractors and shows that the proposed algorithm outperforms other methods.
- 130
- Online Multi-Object Tracking With Instance-Aware Tracker and Dynamic Model Refreshment125
This paper proposes an instance-aware tracker to integrate SOT techniques for MOT by encoding awareness both within and between target models, and considers response maps from all target models and assigns spatial locations exclusively to optimize the overall accuracy.
- 121
- Learning Target-aware Representation for Visual Tracking via Informative Interactions83
A novel backbone architecture with multiple branch-wise interactions inside the Siamese-like backbone networks (InBN) that injects the target information to different stages of the backbone network, leading to better target-perception of candidate feature representation with negligible computation cost.
- AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild76
This work introduces AnimalTrack, a dedicated benchmark for multi-animal tracking in the wild and to understand how existing MOT algorithms perform on AnimalTrack and provide baselines for future comparison, extensively evaluate 14 state-of-the-art representative trackers.
- 65
- Context-Guided Spatio-Temporal Video Grounding65
A novel framework, context-guided STVG (CG-STVG), which mines discriminative instance context for object in videos and applies it as a supplementary guidance for target localization for more accurate target localization.
- Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning64
A surprisingly simple yet effective dual-prompt learning network (dubbed DPLNet) for training-efficient multimodal semantic segmentation, which achieves new state-of-the-art performance or is on a par with other complex approaches on four RGB-D/T semantic segmentation datasets while satisfying parameter efficiency.
- Accurate and Fast Compressed Video Captioning63
A simple yet effective end-to-end transformer in the compressed domain for video captioning that enables learning from the compressed video for captioning and can achieve state-of-the-art performance on different benchmarks while running almost 2× faster than existing approaches.
- PIDray: A Large-Scale X-ray Benchmark for Real-World Prohibited Item Detection61
A tree-like structure is adopted to suppress the influence of the long-tailed issue in the PIDray dataset, where the first course-grained node is tasked with the binary classification to alleviate the influence of head category, while the subsequent fine-grained node is dedicated to the specific tasks of the tail categories.
- 48
- 39
- Robust Domain Adaptive Object Detection With Unified Multi-Granularity Alignment38
A unified multi-granularity alignment (MGA)-based detection framework for domain-invariant feature learning and an adaptive exponential moving average (AEMA) strategy that explores model assessments for model update to improve pseudo labels and alleviate local misalignment problem, boosting detection robustness.
- 35
- Transparent Object Tracking Benchmark34
A novel tracker is introduced, named TransATOM, which leverages transparency features for tracking and surpasses all 25 evaluated approaches by a large margin and is expected to facilitate future research and application of transparent object tracking in both the academia and industry.
- Neural Radiance Fields in Medical Imaging: A Survey29
This paper presents a comprehensive examination of applications of NeRFs in medical imaging, highlighting four imminent challenges, including fundamental imaging principles, inner structure requirement, object boundary definition, and color density significance.
- VisDrone-MOT2020: The Vision Meets Drone Multiple Object Tracking Challenge Results27
The VisDrone-MOT2020 consists of 79 challenging video sequences, including 56 videos for training, 7 videos for validation and 17 videos for evaluation, which feature 12 participating MOT algorithms.
- 26
- Robust Visual Tracking via Local-Global Correlation Filter26
This work proposes a novel local-global correlation filter (LGCF) for object tracking that utilizes both local-based and global-based strategies, and effectively combines these two strategies by exploiting the relationship of circular shifts among local object parts and global target for their motion models to preserve the structure of object.
- 25
- Graph Correspondence Transfer for Person Re-Identification25
The GCT model formulates person re-identification as an off-line graph matching and on-line correspondence transferring problem and can handle spatial misalignment caused by large variations in view angles and human poses owing to the benefits of patch-wise graph matching.
- Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers23
This paper introduces UniST, a Unified Style Transfer framework for both images and videos, which improves computational efficiency while maintains style transfer performance, and presents a simple yet effective axial multi-head self-attention (AMSA) for DIT.
- Divert More Attention to Vision-Language Object Tracking22
This paper introduces a novel framework to improve tracking by learning a unified-adaptive VL representation, where the cores are the proposed asymmetric architecture search and modality mixer (ModaMixer) and introduces a contrastive loss to align different modalities.
- Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding21
Object queries in the novel Target-Aware Transformer for STVG, directly generated from a given video-text pair, naturally carry target-specific cues, making them adaptive and better interact with multimodal features for learning more discriminative information to improve STVG.
- SSPNet: Scale and spatial priors guided generalizable and interpretable pedestrian attribute recognition21
A novel Scale and Spatial Priors Guided Network (SSPNet) is proposed for PAR, which is mainly composed of the Adaptive Feature Scale Selection (AFSS) and Prior Location Extraction (PLE) modules and achieves superior performance on the PCS dataset for attribute localization in terms of IoU.
- MaGIC: Multi-modality Guided Image Completion21
This paper proposes a novel, simple yet effective method for Multi-modal Guided Image Completion, dubbed MaGIC, which not only supports a wide range of single modality as the guidance, but also adapts to arbitrarily customized combination of these modalities for image completion.
- VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results21
This work collects a large-scale dataset and organizes the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments in the related fields.
- 20
- Weighted bilinear coding over salient body parts for person re-identification20
This work proposes a novel weighted bilinear coding (WBC) framework for local feature aggregation in CNN networks to pursue more representative and discriminative feature representations, which can adapt to other state-of-the-art methods and improve their performance.
- 20
- Unsupervised Domain Adaptive Detection with Network Stability Analysis18
This work introduces a novel simple but effective Network Stability Analysis (NSA) framework that considers various disturbances for domain adaptation, and explores three types of perturbations including heavy and light image-level disturbances and instance-level disturbance.
- TracKlinic: Diagnosis of Challenge Factors in Visual Tracking18
A thorough study is conducted on ten state-of-the-art trackers on nine challenge factors, and results suggest that heavy shape variation and occlusion are the two most challenging factors faced by most trackers.
- 17
- Flow-Guided Diffusion for Video Inpainting17
The Flow-Guided Diffusion model for Video Inpainting is introduced, a novel approach that significantly enhances temporal consistency and inpainting quality via reusing an off-the-shelf image generation diffusion model and introduces a model-agnostic flow-guided latent interpolation technique.
- 17
- GL-GAN: Adaptive global and local bilevel optimization for generative adversarial network17
An adaptive global and local bilevel optimization model (GL-GAN) is introduced that achieves the generation of high-resolution images in a complementary and promoting way, where global optimization is to optimize the whole images and local is only to optimize the low-quality areas.
- LaMOT: Language-Guided Multi-Object Tracking16
Language-Guided MOT, a unified task framework, and LaMOT, a corresponding large-scale benchmark, which encompasses diverse scenarios and language descriptions and comprises 1,660 sequences from 4 different datasets are introduced.
- 16
- 16
- 16
- 15
- Scene Parsing Via Dense Recurrent Neural Networks With Attentional Selection14
This paper proposes dense RNNs for scene labeling by exploring various long-range semantic dependencies among image units and develops an end-to-end scene labeling system integrating with convolutional neural networks (CNNs).
- Semantic-aware label placement for augmented reality in street view12
This paper proposes a semantic-aware task-specific label placement method by identifying potentially important image regions through a novel feature map, which is referred to as guidance map, and encodes the constraints for placing labels in an optimization problem to obtain the final label layout.
- PRVQL: Progressive Knowledge-Guided Refinement for Robust Egocentric Visual Query Localization11
Compared to previous methods, the PRVQL, besides the given object cues, enjoys additional crucial target information from a video as guidance to refine features, and hence enhances EgoVQL in complicated scenes.
- High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion11
A novel GAN inversion approach for image inpainting that qualitatively and quantitatively outperforms other state-of-the-arts and it supports the completion of out-of-domain images effectively, and a simple yet effective Soft-update Mean Latent module to capture more diversified in-domain patterns for generating high-fidelity textures for massive corruptions.
- AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes11
A simple, effective, and generic method to predict pedestrian attributes to support general reidentification (Re-ID) embedding, and achieves consistent improvements in multi-object tracking accuracy (MOTA), higher order tracking accuracy (HOTA), association accuracy (AssA), IDs, and IDF1 scores.
- OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding10
A new STVG task that aims at localizing spatially and temporally all targets mentioned in the textual query from videos, dubbed OmniSTVG, and a simple yet effective approach, named OmniTube, which, drawing inspiration from Transformer-based STVG methods, is specially designed for OmniSTVG and demonstrates promising results.
- 10
- Deficiency-Aware Masked Transformer for Video Inpainting10
A dual-modality-compatible inpainting framework called Deficiency-aware Masked Transformer (DMT), which offers three key advantages including benefiting the hallucination of deficiency cases and significantly outperforms previous solutions.
- ClsGAN: Selective Attribute Editing Model based on Classification Adversarial Network10
A novel selective attribute editing model based on classification adversarial network (referred to as ClsGAN) that shows good balance between attribute transfer accuracy and photo-realistic images is proposed and performs favorably against state-of-the-art approaches in image quality and transfer accuracy.
- 10
- Robust tracking based on local structural cell graph10
A simple yet robust tracking algorithm based on local structural cell graph (LSCG) that outperforms several state-of-the-art trackers and exploits both partial and spatial information of the target via representing the object with local structural cells (L SCs) and constructing a graph to model the spatial structure between the inner parts of the object.
- Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models9
Analysis reveals how topic distribution and web resource availability influence hallucination frequency, uncovering language-specific biases that impact model accuracy and contributes to the development of more reliable, language-inclusive AI systems.
- Collaborative three-stream transformers for video captioning9
A novel framework, named COllaborative three-Stream Transformers (COST), to model the three parts separately and complement each other for better representation, and proposes a cross-granularity attention module to align the interactions modeled by the three branches of transformers.
- Local Compressed Video Stream Learning for Generic Event Boundary Detection8
A novel compressed video representation learning method for event boundary detection that is fully end-to-end leveraging rich information in the compressed domain, i.e., RGB, motion vectors, residuals, and the internal group of pictures (GOP) structure, without fully decoding the video.
- 8
- DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting6
DP-GTR is the first framework to integrate both document-level and word-level information while exploiting in-context learning to simultaneously improve privacy and utility, effectively bridging local and global DP mechanisms at the individual data point level.
- LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking6
The Low-Resolution Transformer Tracker (LoReTrack) enjoys not only high efficiency owing to reduced computation but also enhanced accuracy by distilling knowledge from the high-resolution tracker, which shows competitive or even better results compared to 384x384 high-resolution Transformer tracker.
- Transferable Adversarial Attack on 3D Object Tracking in Point Cloud6
This work introduces a novel transferable attack network (TAN) to deceive 3D point cloud tracking and demonstrates the proposed TAN is able to not only drastically degrade the victim 3D point cloud tracker, but also effectively deceive other unseen state-of-the-art approaches, posing a new threat to 3D point cloud tracking.
- 6
- Robust visual tracking via bag of superpixels6
A visual tracking method based on Bag of Superpixels (BoS) is proposed, which outperforms several state-of-the-art trackers in visual tracking.
- Part-Based Visual Tracking via Online Weighted P-N Learning6
A novel part-based tracking algorithm using online weighted P-N learning that outperforms the state-of-the-art trackers and uses a substitute strategy to dynamically update the set of LFB, which makes the tracker robust.
- LitAI: Enhancing Multimodal Literature Understanding and Mining with Generative AI5
LitAI is introduced, a novel approach that employs readily available generative AI tools to enhance multimodal information retrieval from literature documents by integrating tools such as optical character recognition (OCR) with generative AI services.
- Cyclic Refiner: Object-Aware Temporal Representation Learning for Multi-view 3D Detection and Tracking5
A cyclic learning mechanism to improve the robustness of multi-view representation learning and tailor an object-aware association strategy for tracking based on the cyclic learning model.
- CGTrack: Cascade Gating Network with Hierarchical Feature Aggregation for UAV Tracking4
This work introduces a novel family of UAV trackers, termed CGTrack, which combines explicit and implicit techniques to expand network capacity within a coarse-to-fine framework, and designs a novel Lightweight Gated Center Head (LGCH) that utilizes gating mechanisms to decouple target-oriented coordinates from previously expanded features, which contain dense local discriminative information.
- Learnable Cross-Scale Sparse Attention Guided Feature Fusion for UAV Object Detection4
A Learnable Cross-scale Sparse Attention (LCSA) guided feature fusion method to improve the performance of UAV object detection and employ a scale-aware loss function to integrate the normalized Wasserstein distance with CIoU in order to improve the incompatibility of IoU for objects with large scale variance.
- PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking4
This work introduces PlanarTrack, a large-scale challenging planar tracking benchmark that is the largest and the most challenging dataset dedicated to planar object tracking, and derives a variant named PlanarTrackBB for generic object tracking from this benchmark.
- Visual Tracking by Local Superpixel Matching with Markov Random Field4
A novel method to track non-rigid and/or articulated objects using superpixel matching and markov random field MRF and it is shown that this method outperforms several state-of-the-art trackers.
- Benchmarking the Robustness of UAV Tracking Against Common Corruptions3
Current trackers are vulnerable to corruptions, indicating more attention needed in enhancing the robustness of UAV trackers, and UAV-C, a large-scale benchmark for assessing robustness of UAV trackers under common corruptions, is proposed.
- Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection3
A novel, simple, yet effective `Augment and Criticize' framework that explores abundant informative samples from unlabeled data for learning more robust detection models, and introduces the Critical Retraining Strategy (CRS) that leverages a learnable network to evaluate the contribution of unlabeling images at different training timestamps.
- 3
- 2
- GSOT3D: Towards Generic 3D Single Object Tracking in the Wild2
A novel benchmark, GSOT3D, that aims at facilitating development of generic 3D single object tracking (SOT) in the wild and a simple yet effective generic 3D tracker, named PROT3D, that localizes the target object via a progressive spatial-temporal network and outperforms all current solutions by a large margin.
- 2
- 2
- Data and Resources Paper: A Multi-granularity Decade-Long Geo-Tagged Twitter Dataset for Spatial Computing2
This paper presents a publicly accessible large-scale geo-tagged Twitter dataset, comprising 95.8 million tweets from 247 countries, spanning from Jan. 2012 to Dec. 2021, and demonstrates the practical utility of it through two applications: human movement modeling and geo-aware Large Language Model (LLM) tuning.
- 2
- Towards bridging the distribution gap: Instance to Prototype Earth Mover’s Distance for distribution alignment2
This work proposes a novel module named Instance to Prototype Earth Mover's Distance (I2PEMD), where shared class-specific prototypes are progressively learned to narrow the distribution gap across different domains or feature subspaces, and EMMD is calculated to take into consideration the cross-class relationships during embedding alignment.
- 2
- 2
- DMTrack: Spatio-Temporal Multimodal Tracking via Dual-Adapter1
This paper explores adapter tuning and introduces a novel dual-adapter architecture for spatio-temporal multimodal tracking, dubbed DMTrack, which achieves promising spatio-temporal multimodal tracking performance with merely 0.93M trainable parameters.
- 1
- 1
- Attention to Trajectory: Trajectory-Aware Open-Vocabulary Tracking1
This paper proposes TRACT, an open-vocabulary tracker that leverages trajectory information to improve both object association and classification in OV-MOT and introduces a Trajectory Consistency Reinforcement (TCR) strategy, that benefits tracking performance by improving target identity and category consistency.
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- Gaussian clustering and quantification of the sperm chromatin dispersion test using convolutional neural networks–
A deep neural network based model for the automation and quantification of the SCD test that is ready for clinical application is established and the DNA fragmentation index is determined using Gaussian clustering, reflecting the natural distribution of halo geometry and is more tolerable to disturbances and sample conditions.
- –
- Design of a new Over-Current Comparator–
During light loads, the PFM over-current comparator switches the regulator to idle mode, therefore, the battery life will be extended and efficiency of the Step-Down regulator is greatly improved.
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.