Fan Ma

papers

638

total citations

papers (18)

VISTA-LLAMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens

CVPR 2024arXiv

citations

Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval

CVPR 2024arXiv

citations

CapHuman: Capture Your Moments in Parallel Universes

CVPR 2024arXiv

citations

Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity

CVPR 2024arXiv

citations

LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels

CVPR 2024arXiv

citations

Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy

CVPR 2025arXiv

citations

Clustering for Protein Representation Learning

CVPR 2024arXiv

citations

BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities

AAAI 2025arXiv

citations

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

AAAI 2025arXiv

citations

InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillation

ICCV 2025arXiv

citations

From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment

ICCV 2025arXiv

citations

Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection

ICLR 2025arXiv

citations

Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion

CVPR 2025arXiv

citations

Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models

AAAI 2025arXiv

citations

Stitching Segments and Sentences towards Generalization in Video-Text Pre-training

AAAI 2024

citations

Fan Ma

papers (18)

SF-Net: Single-Frame Supervision for Temporal Action Localization

MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis

Unified Transformer Tracker for Object Tracking

VISTA-LLAMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens

Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval

CapHuman: Capture Your Moments in Parallel Universes

Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity

LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels

Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy

Clustering for Protein Representation Learning

BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillation

From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment

Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection

Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion

Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models

Stitching Segments and Sentences towards Generalization in Video-Text Pre-training

papers (18)

SF-Net: Single-Frame Supervision for Temporal Action Localization

MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis

Unified Transformer Tracker for Object Tracking

VISTA-LLAMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens

Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval

CapHuman: Capture Your Moments in Parallel Universes

Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity

LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels

Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy

Clustering for Protein Representation Learning

BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillation

From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment

Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection

Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion

Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models

Stitching Segments and Sentences towards Generalization in Video-Text Pre-training