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
- Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking382
The two major novelties: chained structure and paired attentive regression, make CTracker simple, fast and effective, setting new MOTA records on MOT16 and MOT17 challenge datasets (67.6 and 66.6, respectively), without relying on any extra training data.
- Multimodal Industrial Anomaly Detection via Hybrid Fusion297
This paper proposes Multi-3D-Memory (M3DM), a novel multimodal anomaly detection method with hybrid fusion scheme that outperforms the state-of-the-art (SOTA) methods on both detection and segmentation precision on MVTec- 3D AD dataset.
- 126
- Rethinking Reverse Distillation for Multi-Modal Anomaly Detection68
A novel Multi-Modal Reverse Distillation paradigm that consists of a frozen multi-modal teacher encoder to generate distillation targets and a learnable student decoder targeting to restore multi-modal representations from the teacher is presented.
- FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on49
A novel garment perception enhancement technique, termed FitDiT, designed for high-fidelity virtual try-on using Diffusion Transformers (DiT) allocating more parameters and attention to high-resolution features, and introduces frequency-domain learning by customizing a frequency distance loss to enhance high-frequency garment details.
- FOLT: Fast Multiple Object Tracking from UAV-captured Videos Based on Optical Flow47
FOLT adopts a modern detector and light-weight optical flow extractor to extract object detection features and motion features at a minimum cost and outperform existing state-of-the-art methods in UAV-MOT tasks.
- VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model42
VITA-Audio is the first multi-modal large language model capable of generating audio output during the first forward pass, enabling real-time conversational capabilities with minimal latency and significantly outperforms open-source models of similar model size on multiple benchmarks.
- SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking42
A novel siamese tracking algorithm called SiamRCR is proposed, addressing this problem with a simple, light and effective solution, and builds reciprocal links between classification and regression branches, which can dynamically re-weight their losses for each positive sample.
- M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising38
A novel noise-resistant M3DM-NR framework to leveraging strong multi-modal discriminative capabilities of CLIP, which outperforms state-of-the-art methods in 3D-RGB multi-modal noisy anomaly detection.
- Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region32
Compositional Neural Painter is proposed, a novel stroke-based rendering framework which dynamically predicts the next painting region based on the current canvas, instead of dividing the image plane uniformly into painting regions.
- 27
- YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection23
YOLO-Master, a novel YOLO-like framework that introduces instance-conditional adaptive computation for RTOD, is proposed through a Efficient Sparse Mixture-of-Experts (ES-MoE) block that dynamically allocates computational resources to each input according to its scene complexity.
- 23
- 21
- MM-Tracker: Motion Mamba for UAV-platform Multiple Object Tracking19
This work proposes the Motion Mamba Module, which explores both local and global motion features through cross-correlation and bi-directional Mamba Modules for better motion modeling, and designs motion margin loss to effectively improve the detection accuracy of motion blurred objects.
- STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation19
This work presents a simple and efficient single-stage VIS framework based on the instance segmentation method CondInst by adding an extra tracking head and proposes a novel bi-directional spatio-temporal contrastive learning strategy for tracking embedding across frames.
- Dense Scene Multiple Object Tracking with Box-Plane Matching19
The Box-Plane Matching method is proposed to improve the MOT performacne in dense scenes and achieve data association according to the motion similarity and appearance similarity between tracklets and detections.
- 16
- Toward High Quality Facial Representation Learning15
A self-supervised pre-training framework, called Mask Contrastive Face (MCF), with mask image modeling and a contrastive strategy specially adjusted for face domain tasks is proposed, which outperforms the state-of-the-art methods on multiple downstream tasks.
- Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection14
Mamba-YOLO-World is presented, a novel YOLO-based OVD model employing the proposed MambaFusion Path Aggregation Network (MambaFusion-PAN) as its neck architecture and surpasses existing state-of-the-art OVD methods with fewer parameters and FLOPs.
- DMAD: Dual Memory Bank for Real-World Anomaly Detection14
The results show that DMAD surpasses current state-of-the-art methods, highlighting DMAD's capability in handling the complexities of real-world anomaly detection scenarios.
- PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models12
PointSeg is presented, a novel training-free paradigm that leverages off-the-shelf vision foundation models to address 3D scene perception tasks and demonstrates impressive segmentation performance across various datasets, all without training.
- 12
- Fetch and Forge: Efficient Dataset Condensation for Object Detection11
This work proposes DCOD, the first dataset condensation framework for object detection, which operates in two stages: Fetch and Forge, initially storing key localization and classification information into model parameters, and then reconstructing synthetic images via model inversion.
- 11
- DynamicControl: Adaptive Condition Selection for Improved Text-to-Image Generation6
This work proposes a novel framework, DynamicControl, which supports dynamic combinations of diverse control signals, allowing adaptive selection of different numbers and types of conditions, and demonstrates its superiority over existing methods in terms of controllability, generation quality and composability under various conditional controls.
- ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning5
A Dynamic Granularity Rollout (DGR) mechanism to balance exploration between global semantics and local details by dynamically scheduling different noise sources and a Consistent Policy Gradient Optimization that preserves the model's consistency by aligning the current policy with a more stable prior are introduced.
- 5
- CareCom: Generative Image Composition with Calibrated Reference Features4
This work extends the existing generative composition model to multi-reference version, which allows using arbitrary number of foreground reference images, and proposes to calibrate the global and local features of foreground reference images to make them compatible with the background information.
- 4
- IRPO: Boosting Image Restoration via Post-training GRPO3
IRPO is a GRPO-based post-training framework for deterministic restoration models that combines fidelity-oriented and quality-aware feedback with three components: a General Reward for structural fidelity, an Expert Reward that uses a Vision-Language Model as a coarse visual-quality judge, and a Restoration Reward for task-specific low-level cues.
- CustAny: Customizing Anything from A Single Example3
This paper proposes a novel pipeline to construct a large dataset of general objects and build the Multi-Category ID-Consistent (MC-IDC) dataset, and introduces Customizing Anything (CustAny), a zero-shot framework that maintains ID fidelity and supports flexible text editing for general objects.
- 3
- VI3DRM:Towards meticulous 3D Reconstruction from Sparse Views via Photo-Realistic Novel View Synthesis3
The Visual Isotropy 3D Reconstruction Model (VI3DRM), a diffusion-based sparse views 3D reconstruction model that operates within an ID consistent and perspective-disentangled 3D latent space, is introduced, capable of generating highly realistic images that are indistinguishable from real photographs.
- TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement1
The TokenAR framework, specifically focused on a simple but effective token-level enhancement mechanism to address reference identity confusion problem, significantly augments the capabilities of existing AR based methods in conditional image generation, enabling good identity consistency while preserving high quality background reconstruction.
- Evaluation Analysis on Influences of AHP-TOPSIS-Model-Based Artificial Intelligence on College Students Learning1
The novelty of this article lies in the utilization of the AHP-TOPSIS combined evaluation model, which incorporates the advantages of both models and avoids the limitations associated with a single model, such as biased perspectives and low reliability.
- –
- –
- DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning–
The Discriminative Representation Learning (DRL) framework is proposed, and the Decoupled Anchor Supervision (DAS) is designed to alleviate inconsistency and enable comparable feature representations across incremental stages, thereby narrowing the gap between stage-wise local optimization over a subset of data and global inference across all classes.
- –
- AdapNet: Adaptive Noise-Based Network for Low-Quality Image Retrieval–
A novel setting for low-quality image retrieval is introduced, and an innovative adaptive noise-based loss function is introduced, which dynamically adjusts its focus on the gradient in accordance with image quality, thereby augmenting the learning of unknown noisy samples during training and enhancing intra-class compactness.
- An optimized structure on FPGA of key point description in SIFT algorithm–
In Key Point Description, a new method of generating histograms is proposed, to avoid the rotation of adjacent regions and insure the rotational invariance of SIFT algorithm, and in Matching, conventional Euclidean distance is replaced with Hamming distance.
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.