ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Tao Jin

Tao Jin

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 16, 2026, 3:12 AM AMS

23

papers

242

total citations

papers (23)

Gloss Attention for Gloss-Free Sign Language Translation

MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition

FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion

Non-confusing Generation of Customized Concepts in Diffusion Models

DART: Implicit Doppler Tomography for Radar Novel View Synthesis

Borda Regret Minimization for Generalized Linear Dueling Bandits

OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup

Bridging the Gap for Test-Time Multimodal Sentiment Analysis

SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language

Towards Transformer-Based Aligned Generation with Self-Coherence Guidance

Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noises

Diff-Prompt: Diffusion-driven Prompt Generator with Mask Supervision

DATE: Domain Adaptive Product Seeker for E-Commerce

ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation

Open-set Cross Modal Generalization via Multimodal Unified Representation

A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter

OpenFLAME: Federated Visual Positioning System to Enable Large-Scale Augmented Reality Applications

ISMAR 2025arXiv

Active Ranking without Strong Stochastic Transitivity

MPOD123: One Image to 3D Content Generation Using Mask-enhanced Progressive Outline-to-Detail Optimization

Speech Watermarking with Discrete Intermediate Representations

Generalizable Multi-linear Attention Network

Exploring Group Video Captioning with Efficient Relational Approximation

Non-Natural Image Understanding with Advancing Frequency-based Vision Encoders