Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Stan Ziqing LiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works105 from public data
- Single-Shot Refinement Neural Network for Object Detection1,627
This paper proposes a novel single-shot based detector, called RefineDet, that achieves better accuracy than two-stage methods and maintains comparable efficiency of one- stage methods.
- Detection and Tracking Meet Drones Challenge1,344
This work provides a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and concludes the challenge as well as propose future directions.
- 1,147
- UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking799
This work performs a comprehensive quantitative study on the effects of object detection accuracy to the overall MOT performance, using the new large-scale University at Albany DETection and tRACking (UA-DETRAC) benchmark dataset.
- The Visual Object Tracking VOT2016 Challenge Results776
The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
- The Visual Object Tracking VOT2014 Challenge Results588
The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance and introduces a new dataset with full annotation of targets by rotated bounding boxes and per-frame attribute.
- Occlusion-Aware R-CNN: Detecting Pedestrians in a Crowd467
A new occlusion-aware R-CNN (OR-CNN) is proposed to improve the detection accuracy in the crowd and a new aggregation loss is designed to enforce proposals to be close and locate compactly to the corresponding objects.
- 434
- 313
- 292
- 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.
- Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization242
An attention convolutional binary neural tree architecture is presented to address problems for weakly supervised Fine-grained visual categorization and uses the attention transformer module to enforce the network to capture discriminative features.
- Stochastic online AUC maximization223
It is shown that AUC optimization can be equivalently formulated as a convex-concave saddle point problem and a stochastic online algorithm (SOLAM) is proposed which has time and space complexity of one datum.
- 183
- Vision Meets Drones: Past, Present and Future173
The VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South, is described, being the largest such dataset ever published, and enables extensive evaluation and investigation of visual analysis algorithms on the drone platform.
- DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training157
This work introduces a lightweight visual-aware language decoder that only requires the text data for training, easing the burden on the collection of paired data, and proposes a training-free mechanism to reduce the modality gap.
- 145
- ScratchDet: Training Single-Shot Object Detectors From Scratch142
The ScratchDet achieves the state-of-the-art accuracy on PASCAL VOC 2007, 2012 and MS COCO among all the train-from-scratch detectors and even performs better than several one-stage pretrained methods.
- 140
- Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark139
The Space-Time Neighbor-Aware Network (STNNet) is designed as a strong baseline to solve object detection, tracking and counting jointly in dense crowds and performs favorably against the state-of-the-arts.
- Spatial Attention Pyramid Network for Unsupervised Domain Adaptation137
A new spatial attention pyramid network that combines the dense global structure representation and local texture patterns at each spatial location effectively using the spatial attention mechanism to focus on the discriminative regions with context information for domain adaption.
- VisDrone-DET2018: The Vision Meets Drone Object Detection in Image Challenge Results133
A large-scale drone-based dataset, including 8, 599 images with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc, is released, to narrow the gap between current object detection performance and the real-world requirements.
- Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark130
This work collects a large-scale dataset, named as PIDray, which covers various cases in real-world scenarios for prohibited item detection, and designs the selective dense attention network (SDANet), which consists of the dense attention module and the dependency refinement module.
- 120
- 119
- 118
- 99
- Spatiotemporal CNN for Video Object Segmentation98
A unified, end-to-end trainable spatiotemporal CNN model for VOS, which consists of two branches, i.e., the temporal coherence branch and the spatial segmentation branch, which is designed to capture the dynamic appearance and motion cues of video sequences to guide object segmentation.
- Text with Knowledge Graph Augmented Transformer for Video Captioning90
The proposed TextKG method out-performs the best published results by improving 18.7% absolute CIDEr scores on the YouCookII dataset and performs favorably against the state-of-the-art methods.
- 90
- 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.
- Online Spatio-temporal Structural Context Learning for Visual Tracking85
A robust Spatio-Temporal structural context based Tracker (STT) is presented to complete the tracking task in unconstrained environments and the superiority of the proposed tracker over other state-of-the-art trackers is demonstrated.
- Multi-Drone-Based Single Object Tracking With Agent Sharing Network83
An agent sharing network (ASNet) is proposed by self-supervised template sharing and view-aware fusion of the target from multiple drones, which can improve the tracking accuracy significantly compared with single drone tracking.
- VisDrone-VDT2018: The Vision Meets Drone Video Detection and Tracking Challenge Results81
A large-scale video object detection and tracking dataset, which consists of 79 video clips with about 1.5 million annotated bounding boxes in 33, 366 frames, and the evaluation protocol of the VisDrone-VDT2018 challenge and the results of the algorithms on the benchmark dataset are presented.
- Guided Attention Network for Object Detection and Counting on Drones77
This paper proposes a new Guided Attention network (GAnet) to deal with both object detection and counting tasks based on the feature pyramid, and fuse different scales of feature maps by using the proposed weakly-supervised Background Attention between the background and objects for more semantic feature representation.
- 76
- 73
- The Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results66
A significant general improvement of results has been observed, which partly compensate for the more difficult sequences introduced into the dataset in VOT-TIR2016.
- Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph66
A new multi-camera multi-target tracking method based on a space-time-view hyper-graph that encodes higher-order constraints on 3D geometry, appearance, motion continuity, and trajectory smoothness among 2D tracklets within and across different camera views is proposed.
- 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.
- DETRAC: A New Benchmark and Protocol for Multi-Object Tracking63
This work performs a comprehensive quantitative study on the effect of object detection accuracy to the overall MOT performance based on a new large-scale DETection and tRACking (DETRAC) benchmark dataset.
- Learning Semantic Neural Tree for Human Parsing61
A novel semantic neural tree for human parsing is designed, which uses a tree architecture to encode physiological structure of human body, and designs a coarse to fine process in a cascade manner to generate accurate results.
- 60
- 59
- Geometric Hypergraph Learning for Visual Tracking58
A geometric hypergraph learning-based tracking method, which fully exploits high-order geometric relations among multiple correspondences of parts in different frames, and a confidence-aware sampling method is developed to select representative vertices and hyperedges to construct the geometric hyper graph for more robustness and scalability.
- 55
- Single-Shot Scale-Aware Network for Real-Time Face Detection51
This work proposes a scale-aware detection network using a wide scale range of layers associated with appropriate scales of anchors to handle faces with various scales, and describes a new equal density principle to ensure anchors with different scales to be evenly distributed on the image.
- Unsupervised Learning of Multi-Level Descriptors for Person Re-Identification50
A novel coding method named weighted linear coding (WLC) to learn multi-level descriptors from raw pixel data in an unsupervised manner that guarantees the property of saliency with a similarity constraint and has a good balance between the robustness and distinctiveness.
- 47
- Structured Visual Tracking with Dynamic Graph46
This paper introduces a dynamic graph with pairwise Markov property to model the structure information between the inner parts of the target and demonstrates that this structured tracker outperforms several state-of-the-art trackers in occlusion and structure deformations.
- 43
- Learning Non-Uniform Hypergraph for Multi-Object Tracking41
A new near-online MOT algorithm based on non-uniform hypergraph, which can model different degrees of dependencies among tracklets in a unified objective and achieves favorable performance against the state-of-the-art MOT methods.
- Contrast Enhancement Estimation for Digital Image Forensics41
The nature of contrast enhancement as a mapping between pixel values and the distinct characteristics it introduces to the image pixel histogram is taken advantage of, and a new method to estimate contrast enhancement operations from a single image is described.
- ChaLearn Looking at People: IsoGD and ConGD Large-Scale RGB-D Gesture Recognition37
This article proposes a bidirectional long short-term memory (Bi-LSTM) method, determining video division points based on skeleton points, and introduces the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition.
- Rethinking Object Detection in Retail Stores36
A cascaded localization and counting network is presented as a strong baseline, which gradually classifies and regresses the bounding boxes of objects with the predicted numbers of instances enclosed in the bounded boxes, trained in an end-to-end manner.
- Efficient Pig Counting in Crowds with Keypoints Tracking and Spatial-aware Temporal Response Filtering31
This work presented a real-time automated pig counting system in crowds using only one monocular fisheye camera with an inspection robot, and showed that it achieved performance superior to human.
- 29
- 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.
- Data Priming Network for Automatic Check-Out27
A new data priming method is proposed to solve the domain adaptation problem of automatic Check-Out, in which distracting background is removed from the training images using the coarse-to-fine strategy and images with realistic view angles are selected by the pose pruning method.
- End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection26
A new end-to-end compressed video representation learning for event boundary detection that leverages the rich information in the compressed domain, i.e., RGB, motion vectors, residuals, and the internal group of pictures (GOP) structure, withoutfully decoding the video.
- 25
- 25
- 25
- 24
- ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch.24
The ScratchDet achieves the state-of-the-art accuracy on PASCAL VOC 2007, 2012 and MS COCO among all the train-from-scratch detectors and even performs better than several one-stage pretrained methods.
- SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing23
The method does not require the VLM modules or pre-training tasks used in previous work, offering a more direct and efficient way to provide better supervision signals, and providing a novel, simple, and effective solution for instruction-based image editing.
- Multi-Reward as Condition for Instruction-based Image Editing23
A novel training framework to seamlessly integrate the metric output, regarded as multi-reward, into editing models to learn from the imperfect training triplets and build a challenging evaluation benchmark with real-world images/photos and diverse editing instructions, named Real-Edit.
- 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
- Drone Based RGBT Vehicle Detection and Counting: A Challenge19
This paper presents a large-scale vehicle detection and counting benchmark, named DroneVehicle, aiming at advancing visual analysis tasks on the drone platform, and designs two popular tasks with the benchmark, including object detection and object counting.
- Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model14
A training set is collected for the proposed benchmark based on both Panda70M/WebVid raw videos and small-scale TikTok/CapCut edited videos, which boosts the performance on the proposed EditVid-QA benchmark, indicating the effectiveness of highquality training data.
- Structured Context Transformer for Generic Event Boundary Detection14
Structured Context Transformer (or SC-Transformer) is presented to solve the GEBD task, which can be trained in an end-to-end fashion and demonstrates the effectiveness of the proposed method compared to the state-of-the-art methods.
- Thinking With Bounding Boxes: Enhancing Spatio-Temporal Video Grounding via Reinforcement Fine-Tuning13
STVG-o1 is proposed, the first framework that enables off-the-shelf MLLMs to achieve state-of-the-art STVG performance without any architectural modifications and demonstrates strong open-vocabulary generalization across datasets, establishing MLLMs as viable and powerful backbones for precise spatio-temporal grounding.
- A New Projection Space for Separation of Specular-Diffuse Reflection Components in Color Images13
A slope-based region growing method to implement an image segmentation in the specular regions, and to separate the reflection components for each segmented region as well as the state-of-the-art algorithms.
- 10
- 9
- 9
- Exploring the Role of Audio in Video Captioning8
This work presents an audio-visual framework, which aims to fully exploit the potential of the audio modality for captioning, and proposes new local-global fusion mechanisms to improve information exchange across audio and video.
- Evolvement Constrained Adversarial Learning for Video Style Transfer8
This work introduces a novel evolve-sync loss computed by evolvements to replace optical flow and builds an adversarial learning framework, termed as Video Style Transfer Generative Adversarial Network (VST-GAN), which improves upon the MGAN method for image style transfer for more efficient video style transfer.
- CyberV: Cybernetics for Test-time Scaling in Video Understanding7
This work proposes a novel framework inspired by cybernetic principles, redesigning video MLLMs as adaptive systems capable of self-monitoring, self-correction, and dynamic resource allocation during inference, and demonstrates consistent gains on general-purpose benchmarks, such as VideoMME and WorldSense.
- EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation6
EchoFoley is introduced, a new task designed for video-grounded sound generation with both event level local control and hierarchical semantic control and EchoVidia is proposed, a sounding-event-centric agentic generation framework with slow-fast thinking strategy.
- Edit3K: Universal Representation Learning for Video Editing Components6
This paper proposes the first large-scale dataset for editing components of video creation and proposes a novel method that learns to attend to the appearance of editing components regardless of raw materials, which achieves favorable results on editing component retrieval/ recognition compared to the alternative solutions.
- AIPO: Improving Training Objective for Iterative Preference Optimization6
The length exploitation issue during iterative preference optimization is discussed and the training objective for iterative preference optimization is proposed, namely Agreement-aware Iterative Preference Optimization (AIPO).
- 6
- TGT: Text-Grounded Trajectories for Locally Controlled Video Generation5
Text-Grounded Trajectories (TGT), a framework that conditions video generation on trajectories paired with localized text descriptions, and proposes Location-Aware Cross-Attention (LACA) to integrate these signals and adopt a dual-CFG scheme to separately modulate local and global text guidance.
- 5
- Dual-Stream Transformer for Generic Event Boundary Captioning5
A Dual-Stream Transformer with improvements on both video content encoding and captions generation is proposed, and an model is designed to learn discriminative representations for boundary captioning.
- SC-Transformer++: Structured Context Transformer for Generic Event Boundary Detection5
The existing Structured Context Transformer (SC-Transformer) method for GEBD is improved, with a transformer decoder module added after transformer encoders to extract high quality frame features and optical flow is introduced as a new modality.
- 5
- 5
- 5
- 4
- 4
- Referring Layer Decomposition3
RefLayer is presented, a simple baseline designed for prompt-conditioned layer decomposition, achieving high visual fidelity and semantic alignment, and establishes RLD as a well-defined and benchmarkable research task.
- Learning Discriminative Hidden Structural Parts for Visual Tracking3
A discriminative structural part learning method while integrating the structure information, to address the visual tracking problem and adopts Metropolis-Hastings algorithm integrated with the online Support Vector Machine to complete the hidden variable inference task.
- No-Reference Image Quality Metric Based on Visual Quality Saliency3
By introducing two new and simple low-level features, namely sharpness and smoothness, the Visual Quality Saliency based metric (VQSM) can accurately and blindly assesses image quality without any specific design for different distortions.
- Structured Context Learning for Generic Event Boundary Detection1
This paper proposes a novel method for addressingGeneric Event Boundary Detection, called Structured Context Learning, which introduces the Structured Partition of Sequence (SPoS) to provide a structured context for learning temporal information.
- $\mathcal{D}$-Attn: Decomposed Attention for Large Vision-and-Language Models1
Decomposed Attention (D-Attn) is proposed, a more flexible attention architecture for LVLMs, which enables modification of visual token operations without affecting textual-to-textual attention and diagonalize visual-to-visual attention to reduce computation complexity.
- 1
- 1
- –
- VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing–
A comprehensive vlog evaluation framework guided by professional vlog creators and product managers is defined, establishing a taxonomy of six key dimensions, i.e., Creativity, Consistency, Concept Design, Cinematography, Narration, and Pacing, and presents VlogReward, a robust vlog reward model that can provide both fine-grained multi-dimensional scores and actionable feedback for iterative refinement.
- –
- –
- –
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.