Yongming Rao

43

Papers

1,127

Total Citations

Papers (43)

Runtime Neural Pruning

Generative Multimodal Models are In-Context Learners

Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?

MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation

Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model

SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs

PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds

Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion

FineDiving: A Fine-Grained Dataset for Procedure-Aware Action Quality Assessment

Back to Reality: Weakly-Supervised 3D Object Detection With Shape-Guided Label Enhancement

Point-BERT: Pre-Training 3D Point Cloud Transformers With Masked Point Modeling

DenseCLIP: Language-Guided Dense Prediction With Context-Aware Prompting

SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation

FLAG3D: A 3D Fitness Activity Dataset With Language Instruction

DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion

Learning Discriminative Aggregation Network for Video-Based Face Recognition

Attention-Aware Deep Reinforcement Learning for Video Face Recognition

Group-Aware Contrastive Regression for Action Quality Assessment

PoinTr: Diverse Point Cloud Completion With Geometry-Aware Transformers

RandomRooms: Unsupervised Pre-Training From Synthetic Shapes and Randomized Layouts for 3D Object Detection

NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-View Stereo

Towards Interpretable Deep Metric Learning With Structural Matching

Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-Identification

Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models

TCOVIS: Temporally Consistent Online Video Instance Segmentation

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models

AMixer: Adaptive Weight Mixing for Self-Attention Free Vision Transformers

LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection

Unleashing Text-to-Image Diffusion Models for Visual Perception

X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition

Learning Globally Optimized Object Detector via Policy Gradient

Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition

COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysis

Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds

Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and Landmark Estimation

Structure-Preserving Super Resolution With Gradient Guidance

Global Filter Networks for Image Classification

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

NeurIPS 2021arXiv

HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions

P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting

UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models