Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks87 from public data
- Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers230
This work proposes an adaptive tracker with spatio-temporal transformers (named AQA-Track), which adopts simple autoregressive queries to effectively learn spatio-temporal information without many hand-designed components, and designs a novel attention mechanism for the interaction of existing queries to generate a new query in current frame.
- Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation149
The Rotated Multi-Scale In-teraction Network (RMSIN) is introduced, an innovative approach de-signed for the unique demands of RRSIS, surpassing existing state-of-the-art models by a signif-icant margin.
- Aligning and Prompting Everything All at Once for Universal Visual Perception100
APE advances the convergence of detection and grounding by reformulating language-guided grounding as open-vocabulary detection, which efficiently scales up model prompting to thousands of category vocab-ularies and region descriptions while maintaining the ef-fectiveness of cross-modality fusion.
- Towards General Visual-Linguistic Face Forgery Detection67
This work proposes Face Forgery Text Generator (FFTG), a novel annotation pipeline that generates accurate text descriptions by leveraging forgery masks for initial region and type identification, followed by a comprehensive prompting strategy to guide MLLMs in reducing hallucination.
- 63
- 63
- 58
- Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking51
This work designs an effective weak-to-strong self-supervised training framework that aims to narrow the feature distribution gap between labeled and unlabeled frames, and enables SSTrack++ to not only learn a generalizable tracking representation in a low-annotation self-supervised manner, but also makes it possible to simulate realistic appearance and motion variations of target instances in real-world scenarios.
- Towards Language-Guided Visual Recognition via Dynamic Convolutions34
The experimental results not only show the competitive or better performance of LaConvNet against existing multi-modal networks, but also witness the merits of LaConvNet as an unified structure, including compact network, low computational cost and high generalization ability.
- Flow caching for autoregressive video generation26
FlowCache is presented, the first caching framework specifically designed for autoregressive video generation, which introduces a chunkwise caching strategy that dynamically adapts to the unique denoising characteristics of each chunk, complemented by a joint importance-redundancy optimized KV cache compression mechanism that maintains fixed memory bounds while preserving generation quality.
- SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence23
It is found that even the most advanced MLLM still lags behind humans by large margins on SpaCE-10 and a novel hierarchical annotation pipeline is proposed to generate high-quality and diverse question-answer (QA) pairs.
- 23
- UniVST: A Unified Framework for Training-Free Localized Video Style Transfer21
The proposed UniVST adeptly addresses the challenges of preserving the primary object’s style while ensuring temporal consistency and detail preservation, and has been validated to be superior to existing methods in quantitative and qualitative metrics.
- 21
- GraCo: Granularity-Controllable Interactive Segmentation19
An any-granularity mask generator is designed that exploits the semantic property of the pre-trained IS model to automatically gen-erate abundant mask-granularity pairs without requiring additional manual annotation and a granularity-controllable learning strategy that efficiently imparts the granularity controllability to the IS model is proposed.
- Semi-Supervised Counting via Pixel-by-Pixel Density Distribution Modeling16
This paper designs a pixel-wise distribution matching loss to measure the differences in the pixel-wise density distributions between the prediction and the ground-truth, and designs the interleaving consistency self-supervised learning mechanism to learn from unlabeled data efficiently.
- 15
- SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models12
SocialOmni is introduced, an offline diagnostic benchmark that separates three turn-level decisions: identifying who is speaking, deciding when a designated participant should enter at an annotated query time, and determining how that participant should continue the dialogue.
- OBIMD: A Multi-modal Dataset for Contextual Interpretation of Oracle Bone Inscriptions11
The Oracle Bone Inscriptions Multi-modal Dataset (OBIMD), a large-scale, publicly available corpus to provide pixel-aligned rubbing and facsimile images, character-level annotations, and sentence-level transcriptions with corresponding reading sequences, is presented.
- NICE: Improving Panoptic Narrative Detection and Segmentation With Cascading Collaborative Learning11
A unified and effective framework called NICE that can jointly learn these two panoptic narrative recognition tasks, linking PNS and PND in series with the barycenter of segmentation as the anchor, naturally aligns the two tasks and allows them to complement each other for improved performance.
- 9
- Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models8
The Gradient-Regulated MetaPrompt IQA Framework (GRMP-IQA), designed to efficiently adapt the visual-language pre-trained model, CLIP, to IQA tasks, achieving high accuracy even with limited data, is proposed.
- Event-Anchored Frame Selection for Effective Long-Video Understanding7
Event-Anchored Frame Selection (EFS), a hierarchical, event-aware pipeline that partitions the video stream into visually homogeneous temporal segments, which serve as proxies for semantic events and ensures the final keyframe set jointly optimizes for event coverage, query relevance, and visual diversity.
- Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search7
An Attention-Guided Alignment (AGA) framework featuring two innovative components: Attention-Guided Mask (AGM) Modeling and Text Enrichment Module (TEM), which dynamically masks semantically meaningful words by aggregating the attention weight derived from the text encoding process.
- FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification7
FlexiReID is proposed, a flexible framework that supports seven retrieval modes across four modalities: rgb, infrared, sketches, and text, and introduces an adaptive mixture-of-experts (MoE) mechanism to dynamically integrate diverse modality features and a cross-modal query fusion module to enhance multimodal feature extraction.
- 7
- Motion-Aware Caching for Efficient Autoregressive Video Generation6
MotionCache is proposed, a motion-aware cache framework that exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics and employs a coarse-to-fine strategy: an initial warm-up phase establishes semantic coherence, followed by motion-weighted cache reuse that dynamically adjusts update frequencies per token.
- Special issue on weakly supervised learning6
This dissertation aims to provide a history of web exceptionalism from 1989 to 2002, a period chosen in order to explore its roots as well as specific cases up to and including the year in which descriptions of “Web 2.0” began to circulate.
- DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On5
This initial foray into the application of untrained diffusion models in virtual try-on technology potentially paves the way for further exploration and refinement in this industrially and academically valuable field.
- From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors Via LLM-guided Symbolic Reasoning5
A novel framework that expands the capability of standard object detectors beyond mere object recognition to complex event understanding through LLM-guided symbolic reasoning, bridging the semantic gap between object detection and event understanding without requiring expensive taskspecific training.
- UniPTS: A Unified Framework for Proficient Post-Training Sparsity5
The proposed framework, termed UniPTS, is validated to be much superior to existing PTS methods across extensive benchmarks, and amplifies the performance of POT, a recently proposed recipe, from 3.9% to 68.6% when pruning ResNet-50 at 90% sparsity ratio on ImageNet.
- 4
- VisualCor system4
This work presents a context-based actor correlations graph search framework for TV series with excellent ranking accuracy, efficiency, and the ability to reveal human perception, and deploys it onto an online actor correlation search system, VisualCor, which could be viewed as a visualized, content-based simulation of the Renlifang search engine.
- 3
- Adaptive Fuzzy Positive Learning for Annotation-Scarce Semantic Segmentation3
Adaptive Fuzzy Positive Learning (A-FPL) is proposed for correctly learning unlabeled data in a plug-and-play fashion, targeting adaptively encouraging fuzzy positive predictions and suppressing highly probable negatives.
- SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning2
This work proposes SpecEyes, an agentic-level speculative acceleration framework that breaks this sequential bottleneck in agentic multimodal large language models and introduces a cognitive gating mechanism based on answer separability, which quantifies the model's confidence for self-verification without requiring oracle labels.
- OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping2
OmniView-Space is a framework designed to maintain spatial consistency through multimodal egocentric evidence and achieves state-of-the-art performance on single- and multi-image spatial reasoning benchmarks, while reducing reliance on external geometry pipelines.
- Boosting Filter Optimization and Prompt-Guided Decoding for Mixed Degradation Image Restoration2
A simple but effective multiple-in-one IR baseline model that can effectively restore images with both single and mixed degradations is proposed and an efficient Dual Attribute Embedding module is developed that guides the decoder in leveraging degradation-type and semantic related features, significantly improving the model’s performance in mixed degradation restoration scenarios.
- 2
- Towards Efficient Automatic Self-Pruning of Large Language Models2
This work introduces an end-to-end automatic self-pruning framework for LLMs, which efficiently search layer-wise pruning rates and leverages LLMs to autonomously execute the entire evolutionary search process to search for pruning rate configurations.
- Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive Segmentation2
This paper introduces Dynamic Prompt Embedding (DPE) that adaptively processes only regions of interest while avoiding additional overhead from background tokens, and introduces Dynamic Hybrid Attention (DHA), which leverages previous segmentation masks to route tokens through full attention.
- 1
- 1
- An Extensive Benchmark for Single-Round and Multi-Round Instruction-Based Image Editing1
A comprehensive evaluation benchmark designed for single-round and multi-round assessment of IIE models, which simultaneously evaluates both single-round and multi-round instruction-based edits, assessing the precision and consistency of the edits.
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement–
Q-DeepSight is proposed, a think-with-image framework that achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content and demonstrates its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement, effectively closing the loop between assessment and refinement.
- –
- –
- –
- Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models–
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. 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.