Search Results for author:
Found 269 papers, 121 papers with code
Single-Pedestrian Detection Aided by Multi-pedestrian Detection
A probabilistic framework is proposed to model the relationship between the configurations estimated by singleand multi-pedestrian detectors, and to refine the single-pedestrian detection result with multi-pedestrian detection.
Unsupervised Salience Learning for Person Re-identification
In this paper, we propose a novel perspective for person re-identification based on unsupervised salience learning.
Modeling Mutual Visibility Relationship in Pedestrian Detection
In this paper, we propose a mutual visibility deep model that jointly estimates the visibility statuses of overlapping pedestrians.
Multi-source Deep Learning for Human Pose Estimation
Visual appearance score, appearance mixture type and deformation are three important information sources for human pose estimation.
Learning Mid-level Filters for Person Re-identification
In this paper, we propose a novel approach of learning mid-level filters from automatically discovered patch clusters for person re-identification.
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty.
Person Re-identification by Saliency Learning
(3) saliency matching is proposed based on patch matching.
DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
In this paper, we propose deformable deep convolutional neural networks for generic object detection.
Saliency Detection by Multi-Context Deep Learning
Low-level saliency cues or priors do not produce good enough saliency detection results especially when the salient object presents in a low-contrast background with confusing visual appearance.
Learning Deep Representation With Large-Scale Attributes
Experimental results show that the attributes are helpful in learning better features and improving the object detection accuracy by 2. 6% in mAP on the ILSVRC 2014 object detection dataset and 2. 4% in mAP on PASCAL VOC 2007 object detection dataset.
Multi-Task Recurrent Neural Network for Immediacy Prediction
In this paper, we propose to predict immediacy for interacting persons from still images.
Visual Tracking With Fully Convolutional Networks
Instead of treating convolutional neural network (CNN) as a black-box feature extractor, we conduct in-depth study on the properties of CNN features offline pre-trained on massive image data and classification task on ImageNet.
Window-Object Relationship Guided Representation Learning for Generic Object Detections
We propose a representation learning pipeline to use the relationship as supervision for improving the learned representation in object detection.
Factors in Finetuning Deep Model for object detection
Our analysis and empirical results show that classes with more samples have higher impact on the feature learning.
Structured Feature Learning for Pose Estimation
In this paper, we propose a structured feature learning framework to reason the correlations among body joints at the feature level in human pose estimation.
Multi-Bias Non-linear Activation in Deep Neural Networks
It provides great flexibility of selecting responses to different visual patterns in different magnitude ranges to form rich representations in higher layers.
T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
Temporal and contextual information of videos are not fully investigated and utilized.
Object Detection from Video Tubelets with Convolutional Neural Networks
Deep Convolution Neural Networks (CNNs) have shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation.
Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
Learning generic and robust feature representations with data from multiple domains for the same problem is of great value, especially for the problems that have multiple datasets but none of them are large enough to provide abundant data variations.
End-To-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation
In this paper, we propose a novel end-to-end framework for human pose estimation that combines DCNNs with the expressive deformable mixture of parts.
Factors in Finetuning Deep Model for Object Detection With Long-Tail Distribution
Our analysis and empirical results show that classes with more samples have higher impact on the feature learning.
STCT: Sequentially Training Convolutional Networks for Visual Tracking
To further improve the robustness of each base learner, we propose to train the convolutional layers with random binary masks, which serves as a regularization to enforce each base learner to focus on different input features.
Crafting GBD-Net for Object Detection
The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO.
CRF-CNN: Modeling Structured Information in Human Pose Estimation
In a classical neural network, there is no message passing between neurons in the same layer.
Zoom Out-and-In Network with Recursive Training for Object Proposal
In this paper, we propose a zoom-out-and-in network for generating object proposals.
Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance.
Ranked #6 on
Multi-Label Classification
on NUS-WIDE
Object Detection in Videos with Tubelet Proposal Networks
Object detection in videos has drawn increasing attention recently with the introduction of the large-scale ImageNet VID dataset.
ViP-CNN: Visual Phrase Guided Convolutional Neural Network
In this paper, each visual relationship is considered as a phrase with three components.
Learning Chained Deep Features and Classifiers for Cascade in Object Detection
In this CC-Net, the cascaded classifier at a stage is aided by the classification scores in previous stages.
Multi-Context Attention for Human Pose Estimation
We further combine the holistic attention model, which focuses on the global consistency of the full human body, and the body part attention model, which focuses on the detailed description for different body parts.
Ranked #8 on
Pose Estimation
on Leeds Sports Poses
Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
This paper addresses the problem of depth estimation from a single still image.
Ranked #14 on
Depth Estimation
on NYU-Depth V2
Learning Cross-Modal Deep Representations for Robust Pedestrian Detection
Then, the learned feature representations are transferred to a second deep network, which receives as input an RGB image and outputs the detection results.
Quality Aware Network for Set to Set Recognition
In this paper, the quality aware network (QAN) is proposed to confront this problem, where the quality of each sample can be automatically learned although such information is not explicitly provided in the training stage.
Ranked #6 on
Face Verification
on YouTube Faces DB
Learning Deep Representations for Scene Labeling with Semantic Context Guided Supervision
The experiments show that our proposed method makes deep models learn more discriminative feature representations without increasing model size or complexity.
Scene Graph Generation from Objects, Phrases and Region Captions
Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations, and other context information.
Ranked #2 on
Object Detection
on Visual Genome
Learning Feature Pyramids for Human Pose Estimation
We investigate our method on two standard benchmarks for human pose estimation.
Ranked #6 on
Pose Estimation
on Leeds Sports Poses
Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism
The visibility map of the target is learned and used for inferring the spatial attention map.
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection
A key observation is that it is difficult to classify anchors of different sizes with the same set of features.
Ranked #2 on
Region Proposal
on COCO test-dev
Visual Question Generation as Dual Task of Visual Question Answering
Recently visual question answering (VQA) and visual question generation (VQG) are two trending topics in the computer vision, which have been explored separately.
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
In this study, we introduce a novel compact motion representation for video action recognition, named Optical Flow guided Feature (OFF), which enables the network to distill temporal information through a fast and robust approach.
Ranked #36 on
Action Recognition
on UCF101
Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
Recent works have shown that exploiting multi-scale representations deeply learned via convolutional neural networks (CNN) is of tremendous importance for accurate contour detection.
Monocular Depth Estimation using Multi-Scale Continuous CRFs as Sequential Deep Networks
Depth cues have been proved very useful in various computer vision and robotic tasks.
Style Aggregated Network for Facial Landmark Detection
In this work, we propose a style-aggregated approach to deal with the large intrinsic variance of image styles for facial landmark detection.
Ranked #2 on
Facial Landmark Detection
on AFLW-Front
(Mean NME metric)
3D Human Pose Estimation in the Wild by Adversarial Learning
Instead of defining hard-coded rules to constrain the pose estimation results, we design a novel multi-source discriminator to distinguish the predicted 3D poses from the ground-truth, which helps to enforce the pose estimator to generate anthropometrically valid poses even with images in the wild.
Ranked #1 on
Monocular 3D Human Pose Estimation
on Human3.6M
(Use Video Sequence metric)
Learnable Histogram: Statistical Context Features for Deep Neural Networks
Statistical features, such as histogram, Bag-of-Words (BoW) and Fisher Vector, were commonly used with hand-crafted features in conventional classification methods, but attract less attention since the popularity of deep learning methods.
Quantization Mimic: Towards Very Tiny CNN for Object Detection
To the best of our knowledge, our method, called Quantization Mimic, is the first one focusing on very tiny networks.
Attention-Aware Compositional Network for Person Re-identification
AACN consists of two main components: Pose-guided Part Attention (PPA) and Attention-aware Feature Composition (AFC).
PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
Depth estimation and scene parsing are two particularly important tasks in visual scene understanding.
Ranked #15 on
Depth Estimation
on NYU-Depth V2
Mask-Guided Contrastive Attention Model for Person Re-Identification
We may be the first one to successfully introduce the binary mask into person ReID task and the first one to propose region-level contrastive learning.
Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning
We focus on the one-shot learning for video-based person re-Identification (re-ID).
Collaborative and Adversarial Network for Unsupervised Domain Adaptation
In this paper, we propose a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN) through domain-collaborative and domain-adversarial training of neural networks.
Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking
In addition, inter-object relations are mostly modeled in a symmetric way, which we argue is not an optimal setting.
Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation
Generating scene graph to describe all the relations inside an image gains increasing interests these years.
Ranked #1 on
Scene Graph Generation
on VRD
Crowd Counting using Deep Recurrent Spatial-Aware Network
Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera's perspective that causes huge appearance variations in people's scales and rotations.
Person Search via A Mask-Guided Two-Stream CNN Model
In this work, we tackle the problem of person search, which is a challenging task consisted of pedestrian detection and person re-identification~(re-ID).
Neural Network Encapsulation
Motivated by the routing to make higher capsule have agreement with lower capsule, we extend the mechanism as a compensation for the rapid loss of information in nearby layers.
Deep Kalman Filtering Network for Video Compression Artifact Reduction
In this paper, we model the video artifact reduction task as a Kalman filtering procedure and restore decoded frames through a deep Kalman filtering network.
Dividing and Aggregating Network for Multi-view Action Recognition
We then train view-specific action classifiers based on the view-specific representation for each view and a view classifier based on the shared representation at lower layers.
Deep Learning for Generic Object Detection: A Survey
Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images.
DVC: An End-to-end Deep Video Compression Framework
Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information.
FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction
The basic principles in designing convolutional neural network (CNN) structures for predicting objects on different levels, e. g., image-level, region-level, and pixel-level are diverging.
Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
In this paper, we propose a unified Multi-Object Tracking (MOT) framework learning to make full use of long term and short term cues for handling complex cases in MOT scenes.
Hybrid Task Cascade for Instance Segmentation
In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation.
Ranked #32 on
Object Detection
on COCO-O
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction
In order to address this issue, we propose a data-driven state refinement module for LSTM network (SR-LSTM), which activates the utilization of the current intention of neighbors, and jointly and iteratively refines the current states of all participants in the crowd through a message passing mechanism.
Multi-person Articulated Tracking with Spatial and Temporal Embeddings
Our framework consists of two main components,~\ie~SpatialNet and TemporalNet.
GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
We present an efficient 3D object detection framework based on a single RGB image in the scenario of autonomous driving.
Ranked #18 on
Vehicle Pose Estimation
on KITTI Cars Hard
Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
To this end, we first leverage a stand-alone module to transform the input data from 2D image plane to 3D point clouds space for a better input representation, then we perform the 3D detection using PointNet backbone net to obtain objects 3D locations, dimensions and orientations.
Feature Intertwiner for Object Detection
We argue that the reliable set could guide the feature learning of the less reliable set during training - in spirit of student mimicking teacher behavior and thus pushing towards a more compact class centroid in the feature space.
Ranked #134 on
Object Detection
on COCO test-dev
Libra R-CNN: Towards Balanced Learning for Object Detection
In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level.
Ranked #149 on
Object Detection
on COCO test-dev
Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation
To address this problem, it is a good choice to learn to segment with weak supervision from bounding boxes.
Weakly-supervised Learning
Weakly supervised Semantic Segmentation
+1
PRUNING WITH HINTS: AN EFFICIENT FRAMEWORK FOR MODEL ACCELERATION
Hints can improve the performance of student model by transferring knowledge from teacher model.
Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction
Finally, a GCC module is applied to model the correlation between all regions by computing a global correlation feature as a weighted sum of all regional features, with the weights being calculated as the similarity between the corresponding region pairs.
Online Hyper-parameter Learning for Auto-Augmentation Strategy
Data augmentation is critical to the success of modern deep learning techniques.
AM-LFS: AutoML for Loss Function Search
The key contribution of this work is the design of search space which can guarantee the generalization and transferability on different vision tasks by including a bunch of existing prevailing loss functions in a unified formulation.
Improving Action Localization by Progressive Cross-stream Cooperation
Specifically, we first generate a larger set of region proposals by combining the latest region proposals from both streams, from which we can readily obtain a larger set of labelled training samples to help learn better action detection models.
MMDetection: Open MMLab Detection Toolbox and Benchmark
In this paper, we introduce the various features of this toolbox.
Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments
Firstly, the global-global alignment in the Global Contrast (GC) module is for matching the global contexts of images and descriptions.
Ranked #19 on
Text based Person Retrieval
on CUHK-PEDES
Crowd Counting with Deep Structured Scale Integration Network
Automatic estimation of the number of people in unconstrained crowded scenes is a challenging task and one major difficulty stems from the huge scale variation of people.
Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection
We formulate the CRF graphical model that involves message-passing of feature-feature, feature-prediction, and prediction-prediction, from the coarse scale to the finer scale, to update the features and the corresponding predictions.
GradNet: Gradient-Guided Network for Visual Object Tracking
In this work, we propose a novel gradient-guided network to exploit the discriminative information in gradients and update the template in the siamese network through feed-forward and backward operations.
Ranked #3 on
Visual Object Tracking
on OTB-2015
(Precision metric)
IntersectGAN: Learning Domain Intersection for Generating Images with Multiple Attributes
For example, given two image domains $X_1$ and $X_2$ with certain attributes, the intersection $X_1 \cap X_2$ denotes a new domain where images possess the attributes from both $X_1$ and $X_2$ domains.
Improving One-shot NAS by Suppressing the Posterior Fading
In this paper, we analyse existing weight sharing one-shot NAS approaches from a Bayesian point of view and identify the posterior fading problem, which compromises the effectiveness of shared weights.
TRB: A Novel Triplet Representation for Understanding 2D Human Body
In this paper, we propose the Triplet Representation for Body (TRB) -- a compact 2D human body representation, with skeleton keypoints capturing human pose information and contour keypoints containing human shape information.
A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection
Alternatively, to access much more natural-looking pedestrians, we propose to augment pedestrian detection datasets by transforming real pedestrians from the same dataset into different shapes.
Computation Reallocation for Object Detection
However, classification allocation pattern is usually adopted directly to object detector, which is proved to be sub-optimal.
Learning 3D Human Shape and Pose from Dense Body Parts
Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods.
Ranked #75 on
3D Human Pose Estimation
on 3DPW
(MPJPE metric)
3D human pose and shape estimation
3D Human Reconstruction
+3
EcoNAS: Finding Proxies for Economical Neural Architecture Search
While many methods have been proposed to improve the efficiency of NAS, the search progress is still laborious because training and evaluating plausible architectures over large search space is time-consuming.
Equalization Loss for Long-Tailed Object Recognition
Based on it, we propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories by simply ignoring those gradients for rare categories.
Ranked #17 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Channel Pruning Guided by Classification Loss and Feature Importance
To this end, we propose a new strategy to suppress the influence of unimportant features (i. e., the features will be removed at the next pruning stage).
Content Adaptive and Error Propagation Aware Deep Video Compression
Therefore, the encoder is adaptive to different video contents and achieves better compression performance by reducing the domain gap between the training and testing datasets.
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics.
Ranked #4 on
3D Action Recognition
on Assembly101
Location-Aware Feature Selection Text Detection Network
However, they are behind in accuracy comparing with recent segmentation-based text detectors.
Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection
In this paper, we propose a general and efficient pre-training paradigm, Montage pre-training, for object detection.
Scope Head for Accurate Localization in Object Detection
Existing anchor-based and anchor-free object detectors in multi-stage or one-stage pipelines have achieved very promising detection performance.
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
Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation
The modules of HGG can be trained end-to-end with the keypoint detection network and is able to supervise the grouping process in a hierarchical manner.
Ranked #3 on
Keypoint Detection
on OCHuman
Whole-Body Human Pose Estimation in the Wild
This paper investigates the task of 2D human whole-body pose estimation, which aims to localize dense landmarks on the entire human body including face, hands, body, and feet.
Ranked #8 on
2D Human Pose Estimation
on COCO-WholeBody
Rethinking Pseudo-LiDAR Representation
Based on this observation, we design an image based CNN detector named Patch-Net, which is more generalized and can be instantiated as pseudo-LiDAR based 3D detectors.
BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation
(2) The object categories at the training and inference stages have no overlap, leaving the inter-class gap.
Exploring the Hierarchy in Relation Labels for Scene Graph Generation
By assigning each relationship a single label, current approaches formulate the relationship detection as a classification problem.
Improving Deep Video Compression by Resolution-adaptive Flow Coding
In this work, we propose a new framework called Resolution-adaptive Flow Coding (RaFC) to effectively compress the flow maps globally and locally, in which we use multi-resolution representations instead of single-resolution representations for both the input flow maps and the output motion features of the MV encoder.
SAMOT: Switcher-Aware Multi-Object Tracking and Still Another MOT Measure
Besides, we propose a new MOT evaluation measure, Still Another IDF score (SAIDF), aiming to focus more on identity issues. This new measure may overcome some problems of the previous measures and provide a better insight for identity issues in MOT.
Once Quantized for All: Progressively Searching for Quantized Compact Models
Automatic search of Quantized Neural Networks (QNN) has attracted a lot of attention.
Improving Auto-Augment via Augmentation-Wise Weight Sharing
On CIFAR-10, we achieve a top-1 error rate of 1. 24%, which is currently the best performing single model without extra training data.
Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search
Therefore, we propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides.
Category-specific Semantic Coherency Learning for Fine-grained Image Recognition
Existing deep learning based weakly supervised fine-grained image recognition (WFGIR) methods usually pick out the discriminative regions from the high-level feature (HLF) maps directly.
Adaptive Gradient Method with Resilience and Momentum
Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some recent influential attempts would like to adaptively control the parameter-wise learning rate (e. g., Adam and RMSProp).
Evolving Search Space for Neural Architecture Search
The automation of neural architecture design has been a coveted alternative to human experts.
Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
As a special design of this transformer, the information encoded in the encoder is different from that in the decoder, i. e. the encoder encodes temporal-channel information of multiple frames while the decoder decodes the spatial-channel information for the current frame in a voxel-wise manner.
Full Matching on Low Resolution for Disparity Estimation
To this end, we first propose to decompose the full matching task into multiple stages of the cost aggregation module.
Direct Depth Learning Network for Stereo Matching
To make the Adaptive-Grained Depth Refinement stage robust to the coarse depth and adaptive to the depth range of the points, the Granularity Uncertainty is introduced to Adaptive-Grained Depth Refinement stage.
DETR for Crowd Pedestrian Detection
Furthermore, the bipartite match of ED harms the training efficiency due to the large ground truth number in crowd scenes.
Inception Convolution with Efficient Dilation Search
To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed.
Aggregation With Feature Detection
Aggregating features from different depths of a network is widely adopted to improve the network capability.
Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction
In contrast to previous works directly considering multi-scale feature maps obtained from the inner layers of a primary CNN architecture, and simply fusing the features with weighted averaging or concatenation, we propose a probabilistic graph attention network structure based on a novel Attention-Gated Conditional Random Fields (AG-CRFs) model for learning and fusing multi-scale representations in a principled manner.
Real-Time Visual Object Tracking via Few-Shot Learning
Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot Learning (FSL).
Higher Performance Visual Tracking with Dual-Modal Localization
Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy.
Gradient Regularized Contrastive Learning for Continual Domain Adaptation
To better understand this issue, we study the problem of continual domain adaptation, where the model is presented with a labelled source domain and a sequence of unlabelled target domains.
PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
Regression-based methods have recently shown promising results in reconstructing human meshes from monocular images.
Ranked #5 on
3D Human Pose Estimation
on AGORA
(using extra training data)
3D human pose and shape estimation
3D Human Reconstruction
+2
Delving into Localization Errors for Monocular 3D Object Detection
Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging.
3D Object Detection From Monocular Images
Autonomous Driving
+3
Layerwise Optimization by Gradient Decomposition for Continual Learning
The gradient for update should be close to the gradient of the new task, consistent with the gradients shared by all old tasks, and orthogonal to the space spanned by the gradients specific to the old tasks.
ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search
Human pose estimation has achieved significant progress in recent years.
Ranked #23 on
Pose Estimation
on COCO test-dev
AutoSampling: Search for Effective Data Sampling Schedules
Data sampling acts as a pivotal role in training deep learning models.
Mutual CRF-GNN for Few-Shot Learning
In this MCGN, the labels and features of support data are used by the CRF for inferring GNN affinities in a principled and probabilistic way.
GLiT: Neural Architecture Search for Global and Local Image Transformer
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition.
Ranked #498 on
Image Classification
on ImageNet
Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation
Motivated by the significant inter-task correlation, we propose a novel weakly supervised multi-task framework termed as AuxSegNet, to leverage saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation using only image-level ground-truth labels.
Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
In this paper, we propose to learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection.
Ranked #10 on
Monocular 3D Object Detection
on KITTI Cars Moderate
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages.
3D Object Detection From Monocular Images
Depth Estimation
+3
PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
Then, a compact set of the possible combinations for different token pooling and attention sharing mechanisms are constructed.
BN-NAS: Neural Architecture Search with Batch Normalization
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS).
Towards Balanced Learning for Instance Recognition
In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level.
Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images
Following the top-down paradigm, we decompose the task into two stages, i. e. person localization and pose estimation.
Ranked #2 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
Improving the Transferability of Supervised Pretraining with an MLP Projector
The pretrain-finetune paradigm is a classical pipeline in visual learning.
Deep Instance Segmentation with Automotive Radar Detection Points
Automotive radar provides reliable environmental perception in all-weather conditions with affordable cost, but it hardly supplies semantic and geometry information due to the sparsity of radar detection points.
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks.
Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Data
Though a number of point cloud learning methods have been proposed to handle unordered points, most of them are supervised and require labels for training.
A Continuous Mapping For Augmentation Design
Automated data augmentation (ADA) techniques have played an important role in boosting the performance of deep models.
Revisiting the Transferability of Supervised Pretraining: an MLP Perspective
The pretrain-finetune paradigm is a classical pipeline in visual learning.
Accelerating Neural Network Optimization Through an Automated Control Theory Lens
We conduct experiments both from a control theory lens through a phase locus verification and from a network training lens on several models, including CNNs, Transformers, MLPs, and on benchmark datasets.
b-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
Neural Architecture Search (NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural network automatically.
RePre: Improving Self-Supervised Vision Transformer with Reconstructive Pre-training
Recently, self-supervised vision transformers have attracted unprecedented attention for their impressive representation learning ability.
Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization
PL approaches apply pseudo-labels to unlabeled data, and then train the model with a combination of the labeled and pseudo-labeled data iteratively.
MonoDistill: Learning Spatial Features for Monocular 3D Object Detection
Finally, this LiDAR Net can serve as the teacher to transfer the learned knowledge to the baseline model.
Trajectory Forecasting from Detection with Uncertainty-Aware Motion Encoding
Trajectories obtained from object detection and tracking are inevitably noisy, which could cause serious forecasting errors to predictors built on ground truth trajectories.
3D Object Detection from Images for Autonomous Driving: A Survey
3D object detection from images, one of the fundamental and challenging problems in autonomous driving, has received increasing attention from both industry and academia in recent years.
$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
Neural Architecture Search~(NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural networks automatically.
Multi-class Token Transformer for Weakly Supervised Semantic Segmentation
To this end, we propose a Multi-class Token Transformer, termed as MCTformer, which uses multiple class tokens to learn interactions between the class tokens and the patch tokens.
Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest.
DR.VIC: Decomposition and Reasoning for Video Individual Counting
Instead of relying on the Multiple Object Tracking (MOT) techniques, we propose to solve the problem by decomposing all pedestrians into the initial pedestrians who existed in the first frame and the new pedestrians with separate identities in each following frame.
SeCo: Separating Unknown Musical Visual Sounds with Consistency Guidance
Recent years have witnessed the success of deep learning on the visual sound separation task.
Unsupervised Learning of Accurate Siamese Tracking
As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward.
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 #4 on
2D Human Pose Estimation
on COCO-WholeBody
MS Lesion Segmentation: Revisiting Weighting Mechanisms for Federated Learning
In addition, the segmentation loss function in each client is also re-weighted according to the lesion volume for the data during training.
Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains
While recent self-supervised learning methods have achieved good performances with evaluation set on the same domain as the training set, they will have an undesirable performance decrease when tested on a different domain.
Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation
Besides, our DPK makes the performance of the student model positively correlated with that of the teacher model, which means that we can further boost the accuracy of students by applying larger teachers.
TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer
For another, we devise Language Conditioned Vision Transformer that removes external fusion modules and reuses the uni-modal ViT for vision-language fusion at the intermediate layers.
Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
In this study, we focus on transferring knowledge for video classification tasks.
Ranked #1 on
Action Recognition
on ActivityNet
Action Recognition With Motion Diversification and Dynamic Selection
To address this issue, we introduce a Motion Diversification and Selection (MoDS) module to generate diversified spatio-temporal motion features and then select the suitable motion representation dynamically for categorizing the input video.
Ranked #18 on
Action Recognition
on Something-Something V1
Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches
Contrastive-based self-supervised learning methods achieved great success in recent years.
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 #4 on
2D Pose Estimation
on MP-100
NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition
On the video level, a temporal attention module is learned under dual video-level supervisions on both the salient and the non-salient representations.
Ranked #4 on
Action Recognition
on ActivityNet
3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal
Unlike most previous works that directly predict the 3D poses of two interacting hands simultaneously, we propose to decompose the challenging interacting hand pose estimation task and estimate the pose of each hand separately.
Fine-grained Retrieval Prompt Tuning
In this paper, we develop Fine-grained Retrieval Prompt Tuning (FRPT), which steers a frozen pre-trained model to perform the fine-grained retrieval task from the perspectives of sample prompting and feature adaptation.
An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection
We hope this work can provide insights for the image-based 3D detection community under a semi-supervised setting.
ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body and solve the scale variation of different body parts.
Ranked #2 on
2D Human Pose Estimation
on COCO-WholeBody
Towards Frame Rate Agnostic Multi-Object Tracking
In this paper, we propose a Frame Rate Agnostic MOT framework with a Periodic training Scheme (FAPS) to tackle the FraMOT problem for the first time.
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
To address this issue, we propose CLIP2Point, an image-depth pre-training method by contrastive learning to transfer CLIP to the 3D domain, and adapt it to point cloud classification.
Ranked #3 on
Training-free 3D Point Cloud Classification
on ScanObjectNN
(using extra training data)
Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing
In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of loafing, and further propose a new training strategy to strengthen the performance of residual networks.
The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
Long-tail distribution is widely spread in real-world applications.
Boosting Semi-Supervised 3D Object Detection with Semi-Sampling
When training a teacher-student semi-supervised framework, we randomly select gt samples and pseudo samples to both labeled frames and unlabeled frames, making a strong data augmentation for them.
3D-QueryIS: A Query-based Framework for 3D Instance Segmentation
Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness.
ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency
In the learning phase, each agent minimizes the TD error that is dependent on how the subsequent agents have reacted to their chosen action.
Ranked #1 on
SMAC
on SMAC 3s5z_vs_3s6z
Reconstructing Hand-Held Objects from Monocular Video
The key idea is that the hand motion naturally provides multiple views of the object and the motion can be reliably estimated by a hand pose tracker.
GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds
In contrast to previous 3D MAE frameworks, which either design a complex decoder to infer masked information from maintained regions or adopt sophisticated masking strategies, we instead propose a much simpler paradigm.
EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder
These token embeddings are concatenated with a task token and fed into the frozen CLIP transformer to learn point cloud representation.
3D Point Cloud Pre-training with Knowledge Distillation from 2D Images
The recent success of pre-trained 2D vision models is mostly attributable to learning from large-scale datasets.
MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency
Besides, such scenes with progressive masking ratios can also serve to self-distill their intrinsic spatial consistency, requiring to learn the consistent representations from unmasked areas.
Ponder: Point Cloud Pre-training via Neural Rendering
We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering.
Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?
Most existing text-video retrieval methods focus on cross-modal matching between the visual content of videos and textual query sentences.
Ranked #7 on
Video Retrieval
on VATEX
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
In this paper, we propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We introduce the Video Attribute Association mechanism, which leverages the Video-to-Text knowledge to generate textual auxiliary attributes for complementing video recognition.
Ranked #1 on
Zero-Shot Action Recognition
on ActivityNet
Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator
PLEor could leverage pre-trained CLIP model to infer the discrepancies encompassing both pre-defined and unknown subcategories, called category-specific discrepancies, and transfer them to the backbone network trained in the close-set scenarios.
Crossing the Gap: Domain Generalization for Image Captioning
In this paper, we introduce a new setting called Domain Generalization for Image Captioning (DGIC), where the data from the target domain is unseen in the learning process.
Learning Multi-Modal Class-Specific Tokens for Weakly Supervised Dense Object Localization
Weakly supervised dense object localization (WSDOL) relies generally on Class Activation Mapping (CAM), which exploits the correlation between the class weights of the image classifier and the pixel-level features.
Semi-Supervised Semantic Segmentation under Label Noise via Diverse Learning Groups
Each learning group consists of a teacher network, a student network and a novel filter module.
$β$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search
To address the robustness problem, we first benchmark different NAS methods under a wide range of proxy data, proxy channels, proxy layers and proxy epochs, since the robustness of NAS under different kinds of proxies has not been explored before.
Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline
Our Fast-BEV consists of five parts, We novelly propose (1) a lightweight deployment-friendly view transformation which fast transfers 2D image feature to 3D voxel space, (2) an multi-scale image encoder which leverages multi-scale information for better performance, (3) an efficient BEV encoder which is particularly designed to speed up on-vehicle inference.
Learning from pseudo-labels: deep networks improve consistency in longitudinal brain volume estimation
An accurate and robust quantitative measurement of brain volume change is paramount for translational research and clinical applications.
Saliency Guided Contrastive Learning on Scene Images
Despite being feasible, recent works largely overlooked discovering the most discriminative regions for contrastive learning to object representations in scene images.
Multi-Scale Control Signal-Aware Transformer for Motion Synthesis without Phase
As past poses often contain useful auxiliary hints, in this paper, we propose a task-agnostic deep learning method, namely Multi-scale Control Signal-aware Transformer (MCS-T), with an attention based encoder-decoder architecture to discover the auxiliary information implicitly for synthesizing controllable motion without explicitly requiring auxiliary information such as phase.
UniHCP: A Unified Model for Human-Centric Perceptions
When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e. g., 69. 8 mIoU on CIHP for human parsing, 86. 18 mA on PA-100K for attribute prediction, 90. 3 mAP on Market1501 for ReID, and 85. 8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task.
Ranked #1 on
Pose Estimation
on MS-COCO
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting.
Ranked #1 on
Pedestrian Attribute Recognition
on PA-100K
(using extra training data)
Automatically Predict Material Properties with Microscopic Image Example Polymer Compatibility
Computer image recognition with machine learning method can make up the defects of artificial judging, giving accurate and quantitative judgement.
FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead
We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI).
Stimulative Training++: Go Beyond The Performance Limits of Residual Networks
In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of loafing, and further propose a new training scheme as well as three improved strategies for boosting residual networks beyond their performance limits.
Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification
Clothes-invariant feature extraction is critical to the clothes-changing person re-identification (CC-ReID).
PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer
The key to associating the two different representations is our introduced input-dependent Query Initialization module, which could efficiently generate reference points and content queries.
Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection
LiDAR and Radar are two complementary sensing approaches in that LiDAR specializes in capturing an object's 3D shape while Radar provides longer detection ranges as well as velocity hints.
LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark
To the best of our knowledge, we present one of the very first open-source endeavors in the field, LAMM, encompassing a Language-Assisted Multi-Modal instruction tuning dataset, framework, and benchmark.
