ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Feng Cheng

Feng Cheng

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, 3:13 AM AMS

10

papers

863

total citations

papers (10)

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

TALLFormer: Temporal Action Localization with a Long-Memory Transformer

VindLU: A Recipe for Effective Video-and-Language Pretraining

Unified Coarse-to-Fine Alignment for Video-Text Retrieval

LoCoNet: Long-Short Context Network for Active Speaker Detection

Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models

Synthetic Video Enhances Physical Fidelity in Video Synthesis

VideoAuteur: Towards Long Narrative Video Generation

TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types