Jifeng Dai

65

Papers

8,642

Total Citations

Papers (65)

R-FCN: Object Detection via Region-based Fully Convolutional Networks

NeurIPS 2016arXiv

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World

The All-Seeing Project V2: Towards General Relation Comprehension of the Open World

Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing

Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy

SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation

Docopilot: Improving Multimodal Models for Document-Level Understanding

MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism

MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost

HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding

OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis

Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings

Unsupervised Object Detection With LIDAR Clues

Uni-Perceiver: Pre-Training Unified Architecture for Generic Perception for Zero-Shot and Few-Shot Tasks

AutoLoss-Zero: Searching Loss Functions From Scratch for Generic Tasks

Exploring the Equivalence of Siamese Self-Supervised Learning via a Unified Gradient Framework

Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information

Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks

BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

Siamese Image Modeling for Self-Supervised Vision Representation Learning

Video Dehazing via a Multi-Range Temporal Alignment Network With Physical Prior

InternImage: Exploring Large-Scale Vision Foundation Models With Deformable Convolutions

Planning-Oriented Autonomous Driving

Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Flow-Guided Feature Aggregation for Video Object Detection

Deformable Convolutional Networks

An Empirical Study of Spatial Attention Mechanisms in Deep Networks

PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models

FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting

Exploring Cross-Image Pixel Contrast for Semantic Segmentation

Fast Convergence of DETR With Spatially Modulated Co-Attention

VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation

Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation

BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers

FlowFormer: A Transformer Architecture for Optical Flow

VL-LTR: Learning Class-Wise Visual-Linguistic Representation for Long-Tailed Visual Recognition

Frozen CLIP Models Are Efficient Video Learners

Tip-Adapter: Training-Free Adaption of CLIP for Few-Shot Classification

Influence Selection for Active Learning

V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding

LangBridge: Interpreting Image as a Combination of Language Embeddings

Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis

Convolutional Feature Masking for Joint Object and Stuff Segmentation

Instance-Aware Semantic Segmentation via Multi-Task Network Cascades

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Deep Feature Flow for Video Recognition

Fully Convolutional Instance-Aware Semantic Segmentation

Relation Networks for Object Detection

Towards High Performance Video Object Detection

Deformable ConvNets V2: More Deformable, Better Results

Resolution Adaptive Networks for Efficient Inference

Hierarchical Human Parsing With Typed Part-Relation Reasoning

Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs

MCMAE: Masked Convolution Meets Masked Autoencoders

EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought

JourneyDB: A Benchmark for Generative Image Understanding

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks