ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Dan Guo

Dan Guo

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 10:13 AM AMS

22

papers

410

total citations

papers (22)

Iterative Context-Aware Graph Inference for Visual Dialog

Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition

EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer

Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture

EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering

Object-Aware Adaptive-Positivity Learning for Audio-Visual Question Answering

Text-Based Occluded Person Re-identification via Multi-Granularity Contrastive Consistency Learning

Towards Open-Vocabulary Audio-Visual Event Localization

MMAD: Multi-label Micro-Action Detection in Videos

Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration

Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observations

Patch-level Sounding Object Tracking for Audio-Visual Question Answering

Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing

Sign-IDD: Iconicity Disentangled Diffusion for Sign Language Production

ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding

MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights

AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring

Moderating the Generalization of Score-based Generative Model

Audio—Visual Segmentation

PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement

KPA-Tracker: Towards Robust and Real-Time Category-Level Articulated Object 6D Pose Tracking

Data-Free Quantization via Pseudo-label Filtering