Search Results for author:
Found 49 papers, 21 papers with code
Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate
To the best of our knowledge, this is the first public dataset which contains samples with sequential dependence of click and conversion labels for CVR modeling.
The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation
Specifically, by investigating the standard data processing in state-of-the-art approaches mainly including coordinate system transformation and keypoint format transformation (i. e., encoding and decoding), we find that the results obtained by common flipping strategy are unaligned with the original ones in inference.
Ranked #14 on
Pose Estimation
on COCO test-dev
AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation
As AID successfully pushes the performance boundary of human pose estimation problem by considerable margin and sets a new state-of-the-art, we hope AID to be a regular configuration for training human pose estimators.
Ranked #1 on
Multi-Person Pose Estimation
on COCO minival
BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View
As a fast version, BEVDet-Tiny scores 31. 2% mAP and 39. 2% NDS on the nuScenes val set.
Ranked #20 on
Robust Camera Only 3D Object Detection
on nuScenes-C
BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection
Single frame data contains finite information which limits the performance of the existing vision-based multi-camera 3D object detection paradigms.
Ranked #17 on
3D Object Detection
on nuScenes Camera Only
BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deployment
We offer an example of deployment to the TensorRT backend in branch dev2. 0 and show how fast the BEVDet paradigm can be processed on it.
CAFE: Learning to Condense Dataset by Aligning Features
Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one.
DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
In this work, we present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP.
EANet: Enhancing Alignment for Cross-Domain Person Re-identification
Person re-identification (ReID) has achieved significant improvement under the single-domain setting.
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving
Specifically, BEVerse first performs shared feature extraction and lifting to generate 4D BEV representations from multi-timestamp and multi-view images.
Ranked #15 on
Robust Camera Only 3D Object Detection
on nuScenes-C
SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
In this paper, we propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras.
MVSTER: Epipolar Transformer for Efficient Multi-View Stereo
Therefore, we present MVSTER, which leverages the proposed epipolar Transformer to learn both 2D semantics and 3D spatial associations efficiently.
MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
Self-supervised monocular depth estimation is an attractive solution that does not require hard-to-source depth labels for training.
Ranked #1 on
Monocular Depth Estimation
on KITTI
HFT: Lifting Perspective Representations via Hybrid Feature Transformation
In order to reap the benefits and avoid the drawbacks of CBFT and CFFT, we propose a novel framework with a Hybrid Feature Transformation module (HFT).
Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes
To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method.
Structure-Aware Face Clustering on a Large-Scale Graph With 107 Nodes
To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method.
Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark
To mitigate the problem, we propose the Autonomous-driving StreAming Perception (ASAP) benchmark, which is the first benchmark to evaluate the online performance of vision-centric perception in autonomous driving.
Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning
In contrast, multi-frame depth estimation methods improve the depth accuracy thanks to the success of Multi-View Stereo (MVS), which directly makes use of geometric constraints.
A Simple Baseline for Multi-Camera 3D Object Detection
First, we extract multi-scale features and generate the perspective object proposals on each monocular image.
Detachable Novel Views Synthesis of Dynamic Scenes Using Distribution-Driven Neural Radiance Fields
Specifically, it employs a neural representation to capture the scene distribution in the static background and a 6D-input NeRF to represent dynamic objects, respectively.
UCT: Learning Unified Convolutional Networks for Real-time Visual Tracking
Convolutional neural networks (CNN) based tracking approaches have shown favorable performance in recent benchmarks.
Tag-Weighted Topic Model For Large-scale Semi-Structured Documents
We propose a novel method to model the SSDs by a so-called Tag-Weighted Topic Model (TWTM).
Attention-guided Unified Network for Panoptic Segmentation
This paper studies panoptic segmentation, a recently proposed task which segments foreground (FG) objects at the instance level as well as background (BG) contents at the semantic level.
Ranked #24 on
Panoptic Segmentation
on COCO test-dev
Action Machine: Rethinking Action Recognition in Trimmed Videos
On NTU RGB-D, Action Machine achieves the state-of-the-art performance with top-1 accuracies of 97. 2% and 94. 3% on cross-view and cross-subject respectively.
Ranked #1 on
Action Recognition
on UTD-MHAD
State-aware Re-identification Feature for Multi-target Multi-camera Tracking
Multi-target Multi-camera Tracking (MTMCT) aims to extract the trajectories from videos captured by a set of cameras.
Exploiting Offset-guided Network for Pose Estimation and Tracking
Human pose estimation has witnessed a significant advance thanks to the development of deep learning.
FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
Given the results of MTN, we adopt an occlusion-aware Re-ID feature strategy in the pose tracking module, where pose information is utilized to infer the occlusion state to make better use of Re-ID feature.
Instance Scale Normalization for image understanding
Scale variation remains a challenging problem for object detection.
High Performance Visual Object Tracking with Unified Convolutional Networks
In this paper, we propose an end-to-end framework to learn the convolutional features and perform the tracking process simultaneously, namely, a unified convolutional tracker (UCT).
Multi-Stage HRNet: Multiple Stage High-Resolution Network for Human Pose Estimation
Human pose estimation are of importance for visual understanding tasks such as action recognition and human-computer interaction.
WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol.
Ranked #1 on
Face Verification
on IJB-C
(training dataset metric)
SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation
To make a better trade-off between accuracy and efficiency, we propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE).
Pre-trained Language Model for Web-scale Retrieval in Baidu Search
More importantly, we present a practical system workflow for deploying the model in web-scale retrieval.
Masked Face Recognition Challenge: The WebFace260M Track Report
There are second phase of the challenge till October 1, 2021 and on-going leaderboard.
Face-NMS: A Core-set Selection Approach for Efficient Face Recognition
The current research on this problem mainly focuses on designing an efficient Fully-connected layer (FC) to reduce GPU memory consumption caused by a large number of identities.
Hand gesture detection in tests performed by older adults
We have implemented a hand gesture detector to detect the gestures in the hand movement tests and our detection mAP is 0. 782 which is better than the state-of-the-art.
Joint Demand Prediction for Multimodal Systems: A Multi-task Multi-relational Spatiotemporal Graph Neural Network Approach
Despite some recent efforts, existing approaches to multimodal demand prediction are generally not flexible enough to account for multiplex networks with diverse spatial units and heterogeneous spatiotemporal correlations across different modes.
Bike Sharing Demand Prediction based on Knowledge Sharing across Modes: A Graph-based Deep Learning Approach
Bike sharing is an increasingly popular part of urban transportation systems.
WebFace260M: A Benchmark for Million-Scale Deep Face Recognition
For a comprehensive evaluation of face matchers, three recognition tasks are performed under standard, masked and unbiased settings, respectively.
Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline
To the best of our knowledge, this is the first large-scale dataset for gait recognition in the wild.
Dimension Embeddings for Monocular 3D Object Detection
In this paper, we propose a general method to learn appropriate embeddings for dimension estimation in monocular 3D object detection.
A Comprehensive Review on Deep Supervision: Theories and Applications
Deep supervision, or known as 'intermediate supervision' or 'auxiliary supervision', is to add supervision at hidden layers of a neural network.
Hybrid CNN -Interpreter: Interpret local and global contexts for CNN-based Models
Convolutional neural network (CNN) models have seen advanced improvements in performance in various domains, but lack of interpretability is a major barrier to assurance and regulation during operation for acceptance and deployment of AI-assisted applications.
Cross-Mode Knowledge Adaptation for Bike Sharing Demand Prediction using Domain-Adversarial Graph Neural Networks
Existing methods for bike sharing demand prediction are mostly based on its own historical demand variation, essentially regarding it as a closed system and neglecting the interaction between different transportation modes.
Deep trip generation with graph neural networks for bike sharing system expansion
For station-based BSSs, this means planning new stations based on existing ones over time, which requires prediction of the number of trips generated by these new stations across the whole system.
DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving
The established world model holds immense potential for the generation of high-quality driving videos, and driving policies for safe maneuvering.
WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens
World models play a crucial role in understanding and predicting the dynamics of the world, which is essential for video generation.
Generative Design of Crystal Structures by Point Cloud Representations and Diffusion Model
Efficiently generating energetically stable crystal structures has long been a challenge in material design, primarily due to the immense arrangement of atoms in a crystal lattice.
DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation
DriveDreamer-2 is the first world model to generate customized driving videos, it can generate uncommon driving videos (e. g., vehicles abruptly cut in) in a user-friendly manner.
