Search Results for author:
Found 87 papers, 52 papers with code
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.
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 Pretraining at Scale: Transformer-Based Encoding of Transactional Behavior for Fraud Detection
In this work, we introduce an innovative autoregressive model leveraging Generative Pretrained Transformer (GPT) architectures, tailored for fraud detection in payment systems.
OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline
Based on OpenStereo, we conducted experiments and have achieved or surpassed the performance metrics reported in the original paper.
On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving
This has been a significant bottleneck, particularly in the development of common sense reasoning and nuanced scene understanding necessary for safe and reliable autonomous driving.
DREAM+: Efficient Dataset Distillation by Bidirectional Representative Matching
Dataset distillation plays a crucial role in creating compact datasets with similar training performance compared with original large-scale ones.
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.
Introspective Deep Metric Learning
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images.
Unified Single-Stage Transformer Network for Efficient RGB-T Tracking
With this structure, the network can extract fusion features of the template and search region under the mutual interaction of modalities.
Ranked #1 on
Rgb-T Tracking
on GTOT
Evidential Detection and Tracking Collaboration: New Problem, Benchmark and Algorithm for Robust Anti-UAV System
Still, previous works have simplified such an anti-UAV task as a tracking problem, where the prior information of UAVs is always provided; such a scheme fails in real-world anti-UAV tasks (i. e. complex scenes, indeterminate-appear and -reappear UAVs, and real-time UAV surveillance).
One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception
Numerous studies have investigated the pivotal role of reliable 3D volume representation in scene perception tasks, such as multi-view stereo (MVS) and semantic scene completion (SSC).
The 3rd Anti-UAV Workshop & Challenge: Methods and Results
Second, we set up two tracks for the first time, i. e., Anti-UAV Tracking and Anti-UAV Detection & Tracking.
Multi-Prompt with Depth Partitioned Cross-Modal Learning
In recent years, soft prompt learning methods have been proposed to fine-tune large-scale vision-language pre-trained models for various downstream tasks.
OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction
The vision-based perception for autonomous driving has undergone a transformation from the bird-eye-view (BEV) representations to the 3D semantic occupancy.
3D Semantic Occupancy Prediction
3D Semantic Scene Completion from a single RGB image
+3
DyGait: Exploiting Dynamic Representations for High-performance Gait Recognition
This is the first framework on gait recognition that is designed to focus on the extraction of dynamic features.
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving
Towards a more comprehensive perception of a 3D scene, in this paper, we propose a SurroundOcc method to predict the 3D occupancy with multi-camera images.
DiffBEV: Conditional Diffusion Model for Bird's Eye View Perception
Diffusion models naturally have the ability to denoise noisy samples to the ideal data, which motivates us to utilize the diffusion model to get a better BEV representation.
A Simple Baseline for Supervised Surround-view Depth Estimation
The former is achieved by the self-attention module within each view, while the latter is realized by the adjacent attention module, which computes the attention across multi-cameras to exchange the multi-scale representations across surround-view feature maps.
DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation
We propose DiffusionDepth, a new approach that reformulates monocular depth estimation as a denoising diffusion process.
DiM: Distilling Dataset into Generative Model
To the best of our knowledge, we are the first to achieve higher accuracy on complex architectures than simple ones, such as 75. 1\% with ResNet-18 and 72. 6\% with ConvNet-3 on ten images per class of CIFAR-10.
OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception
Towards a comprehensive benchmarking of surrounding perception algorithms, we propose OpenOccupancy, which is the first surrounding semantic occupancy perception benchmark.
DREAM: Efficient Dataset Distillation by Representative Matching
Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling.
DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation
In this way, the proposed DiffTalk is capable of producing high-quality talking head videos in synchronization with the source audio, and more importantly, it can be naturally generalized across different identities without any further fine-tuning.
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.
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.
Token-Label Alignment for Vision Transformers
Data mixing strategies (e. g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs).
OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions
The pretrain-finetune paradigm in modern computer vision facilitates the success of self-supervised learning, which tends to achieve better transferability than supervised learning.
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.
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.
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
Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis
Thus the facial radiance field can be flexibly adjusted to the new identity with few reference images.
Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search
Differentiable architecture search (DARTS) acquires the optimal architectures by optimizing the architecture parameters with gradient descent, which significantly reduces the search cost.
OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression
In this paper, we propose to learn the rank concepts from the rich semantic CLIP latent space.
Ranked #1 on
Few-shot Age Estimation
on MORPH Album2
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
Domain Adaptation of Black-box Predictors (DABP) aims to learn a model on an unlabeled target domain supervised by a black-box predictor trained on a source domain.
FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders
Firstly, randomly masked face images are used to train the reconstruction module in FaceMAE.
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
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.
Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels
This paradigm, however, is prone to significant degeneration under heavy label noise, as the number of clean samples is too small for conventional methods to behave well.
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.
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.
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).
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.
Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing
Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection.
Ranked #1 on
Face Parsing
on Helen
GaitStrip: Gait Recognition via Effective Strip-based Feature Representations and Multi-Level Framework
ECM consists of the Spatial-Temporal feature extractor (ST), the Frame-Level feature extractor (FL) and SPB, and has two obvious advantages: First, each branch focuses on a specific representation, which can be used to improve the robustness of the network.
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.
Crafting Better Contrastive Views for Siamese Representation Learning
For high performance Siamese representation learning, one of the keys is to design good contrastive pairs.
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.
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
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.
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.
Masked Face Recognition Challenge: The InsightFace Track Report
In this workshop, we organize Masked Face Recognition (MFR) challenge and focus on bench-marking deep face recognition methods under the existence of facial masks.
Masked Face Recognition Challenge: The WebFace260M Track Report
There are second phase of the challenge till October 1, 2021 and on-going leaderboard.
Global Filter Networks for Image Classification
Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision have shown great potential in achieving promising performance with fewer inductive biases.
Ranked #9 on
Image Classification
on Stanford Cars
(using extra training data)
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.
An Efficient Training Approach for Very Large Scale Face Recognition
This method adopts Dynamic Class Pool (DCP) for storing and updating the identities features dynamically, which could be regarded as a substitute for the FC layer.
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).
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.
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)
Joint predictions of multi-modal ride-hailing demands: a deep multi-task multigraph learning-based approach
To address this issue, we propose a deep multi-task multi-graph learning approach, which combines two components: (1) multiple multi-graph convolutional (MGC) networks for predicting demands for different service modes, and (2) multi-task learning modules that enable knowledge sharing across multiple MGC networks.
PiaNet: A pyramid input augmented convolutional neural network for GGO detection in 3D lung CT scans
In the first stage, the feature-extraction module is embedded into a classifier network that is trained on a large data set of GGO and non-GGO patches, which are generated by performing data augmentation from a small number of annotated CT scans.
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
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
Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network
To overcome this challenge, we propose the Spatio-Temporal Encoder-Decoder Residual Multi-Graph Convolutional network (ST-ED-RMGC), a novel deep learning model for predicting ride-sourcing demand of various OD pairs.
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.
The Field-of-View Constraint of Markers for Mobile Robot with Pan-Tilt Camera
In the field of navigation and visual servo, it is common to calculate relative pose by feature points on markers, so keeping markers in camera's view is an important problem.
EPOSIT: An Absolute Pose Estimation Method for Pinhole and Fish-Eye Cameras
This paper presents a generic 6DOF camera pose estimation method, which can be used for both the pinhole camera and the fish-eye camera.
Human Following for Wheeled Robot with Monocular Pan-tilt Camera
Human following on mobile robots has witnessed significant advances due to its potentials for real-world applications.
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).
Camera Pose Correction in SLAM Based on Bias Values of Map Points
Firstly, the relationship between the camera pose estimation error and bias values of map points is derived based on the optimized function in VSLAM.
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.
Exploiting Offset-guided Network for Pose Estimation and Tracking
Human pose estimation has witnessed a significant advance thanks to the development of deep learning.
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.
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
Identity-Enhanced Network for Facial Expression Recognition
Facial expression recognition is a challenging task, arguably because of large intra-class variations and high inter-class similarities.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
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
Multi-hierarchical Independent Correlation Filters for Visual Tracking
For visual tracking, most of the traditional correlation filters (CF) based methods suffer from the bottleneck of feature redundancy and lack of motion information.
Optical Flow Based Online Moving Foreground Analysis
Obtained by moving object detection, the foreground mask result is unshaped and can not be directly used in most subsequent processes.
An Efficient Optical Flow Based Motion Detection Method for Non-stationary Scenes
Real-time motion detection in non-stationary scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource.
Motion Detection
Motion Detection In Non-Stationary Scenes
+1
Distractor-aware Siamese Networks for Visual Object Tracking
During the off-line training phase, an effective sampling strategy is introduced to control this distribution and make the model focus on the semantic distractors.
Ranked #11 on
Visual Object Tracking
on VOT2017/18
Optical Flow Based Real-time Moving Object Detection in Unconstrained Scenes
Real-time moving object detection in unconstrained scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource.
High Performance Visual Tracking With Siamese Region Proposal Network
Visual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on multiple benchmarks.
Ranked #7 on
Visual Object Tracking
on VOT2017/18
End-to-end Video-level Representation Learning for Action Recognition
From the frame/clip-level feature learning to the video-level representation building, deep learning methods in action recognition have developed rapidly in recent years.
UCT: Learning Unified Convolutional Networks for Real-time Visual Tracking
Convolutional neural networks (CNN) based tracking approaches have shown favorable performance in recent benchmarks.
End-to-end Flow Correlation Tracking with Spatial-temporal Attention
Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks.
Learning Gating ConvNet for Two-Stream based Methods in Action Recognition
For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme.
Targeted Learning with Daily EHR Data
Electronic health records (EHR) data provide a cost and time-effective opportunity to conduct cohort studies of the effects of multiple time-point interventions in the diverse patient population found in real-world clinical settings.
Evolutionary Approaches to Optimization Problems in Chimera Topologies
In this paper we investigate for the first time the use of Evolutionary Algorithms (EAs) on Ising spin glass instances defined on the Chimera topology.
