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
- Changhong FuSuggested from co-authorship
- Yiming LiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works16 from public data
- HiFT: Hierarchical Feature Transformer for Aerial Tracking326
This work proposes an efficient and effective hierarchical feature transformer (HiFT) for aerial tracking that can efficiently learn the interdependencies among multi-level features, thereby discovering a tracking-tailored feature space with strong discriminability.
- TCTrack: Temporal Contexts for Aerial Tracking271
This work presents TCTrack11, a comprehensive framework to fully exploit temporal contexts for aerial tracking, and proposes an adaptive temporal transformer, which first effectively encodes temporal knowledge in a memory-efficient way, before the temporal knowledge is decoded for accurate adjustment of the similarity map.
- SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking172
A novel attentional Siamese tracker (SiamAPN++) is proposed for real-time UAV tracking and a special attentional aggregation network (AAN) consisting of self-AAN andCrossAAN for raising the representation ability of features eventually is conducted.
- 125
- Towards Real-World Visual Tracking With Temporal Contexts116
This work proposes a two-level framework (TCTrack) that can exploit temporal contexts efficiently and introduces an attention-based temporally adaptive convolution to enhance the spatial features using temporal information, which is achieved by dynamically calibrating the convolution weights.
- Siamese Anchor Proposal Network for High-Speed Aerial Tracking93
A novel two-stage Siamese network-based method for aerial tracking, i.e., stage-1 for high-quality anchor proposal generation, stage-2 for refining the anchor proposal, which can increase the robustness and generalization to different objects with various sizes and make calculation feasible due to the substantial decrease of anchor numbers.
- Tracker Meets Night: A Transformer Enhancer for UAV Tracking88
Evaluations on both the public UAVDark135 benchmark and the newly constructed DarkTrack2021 benchmark show that the task-inspired design enables SCT with significant performance gains for nighttime UAV tracking compared with other top-ranked low-light enhancers.
- Siamese object tracking for unmanned aerial vehicle: a review and comprehensive analysis87
A comprehensive review of leading-edge Siamese trackers is presented, along with an exhaustive UAV-specific analysis based on the evaluation using a typical UAV onboard processor, to explore the deployment of Siamese networks in UAV-based tracking.
- DarkLighter: Light Up the Darkness for UAV Tracking54
This work proposes a low-light image enhancer namely DarkLighter, which dedicates to alleviate the impact of poor illumination and noise iteratively, and is implemented on a typical UAV system.
- Egocentric Prediction of Action Target in 3D41
A large multimodality dataset is proposed of more than 1 million frames of RGB-D and IMU streams, and evaluation metrics based on high-quality 2D and 3D labels from semi-automatic annotation are provided, demonstrating that this new task is worthy of further study by researchers in robotics, vision, and learning communities.
- 29
- Local Perception-Aware Transformer for Aerial Tracking17
The proposed tracker replaces the global encoder by a novel local-recognition encoder, which can model local object details precisely under aerial view through detail-inquiry net and achieves competitive accuracy and robustness in several authoritative aerial benchmarks.
- DiffTF++: 3D-Aware Diffusion Transformer for Large-Vocabulary 3D Generation16
Multi-view reconstruction loss is utilized to fine-tune the diffusion model and triplane decoder, thereby avoiding the negative influence caused by reconstruction errors and improving texture synthesis, and the generative performance is enhanced, especially in texture.
- Collaborative Multi-Modal Coding for High-Quality 3D Generation4
TriMM is presented, the first feed-forward 3D-native generative model that learns from basic multi-modalities and employs a triplane latent diffusion model to generate 3D assets of superior quality, enhancing both the texture and the geometric detail.
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. 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. You will be asked to sign in.