Search Results for author:
Found 9 papers, 7 papers with code
NADER: Neural Architecture Design via Multi-Agent Collaboration
In this paper, we introduce NADER (Neural Architecture Design via multi-agEnt collaboRation), a novel framework that formulates neural architecture design (NAD) as a LLM-based multi-agent collaboration problem.
KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension
To bridge this gap, we introduce the novel challenge of Semantic Keypoint Comprehension, which aims to comprehend keypoints across different task scenarios, including keypoint semantic understanding, visual prompt-based keypoint detection, and textual prompt-based keypoint detection.
TCFormer: Visual Recognition via Token Clustering Transformer
Our dynamic tokens possess two crucial characteristics: (1) Representing image regions with similar semantic meanings using the same vision token, even if those regions are not adjacent, and (2) concentrating on regions with valuable details and represent them using fine tokens.
When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset
With multi-modal joint training, our model achieves state-of-the-art performance on a wide range of pedestrian detection benchmarks, surpassing leading models tailored for specific sensor modality.
Ranked #1 on
Object Detection
on STCrowd
AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks
While traditional AutoML approaches have been successfully applied in several critical steps of model development (e. g. hyperparameter optimization), there lacks a AutoML system that automates the entire end-to-end model production workflow for computer vision.
GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition
Multi-Label Image Recognition (MLIR) is a challenging task that aims to predict multiple object labels in a single image while modeling the complex relationships between labels and image regions.
Ranked #3 on
Multi-Label Classification
on PASCAL VOC 2007
Pose for Everything: Towards Category-Agnostic Pose Estimation
In this paper, we introduce the task of Category-Agnostic Pose Estimation (CAPE), which aims to create a pose estimation model capable of detecting the pose of any class of object given only a few samples with keypoint definition.
Ranked #2 on
Category-Agnostic Pose Estimation
on MP100
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer
Vision transformers have achieved great successes in many computer vision tasks.
Ranked #7 on
2D Human Pose Estimation
on COCO-WholeBody
3D Human Mesh Regression with Dense Correspondence
This paper proposes a model-free 3D human mesh estimation framework, named DecoMR, which explicitly establishes the dense correspondence between the mesh and the local image features in the UV space (i. e. a 2D space used for texture mapping of 3D mesh).
Ranked #1 on
3D Human Reconstruction
on Surreal
