Search Results for author:
Found 183 papers, 103 papers with code
Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation
Captioned images are widely available on the web, while the captions often contain the names of the subjects in the images.
MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond
While most of recent neural rendering works focus on objects and small-scale scenes, developing neural rendering methods for city-scale scenes is of great potential in many real-world applications.
LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models
To this end, we propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model.
InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition
We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition.
Unified Human-Scene Interaction via Prompted Chain-of-Contacts
Based on the definition, UniHSI constitutes a Large Language Model (LLM) Planner to translate language prompts into task plans in the form of CoC, and a Unified Controller that turns CoC into uniform task execution.
PointLLM: Empowering Large Language Models to Understand Point Clouds
The unprecedented advancements in Large Language Models (LLMs) have created a profound impact on natural language processing but are yet to fully embrace the realm of 3D understanding.
WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models
The rise in popularity of ChatGPT and GPT-4 has significantly accelerated the development of large models, leading to the creation of numerous impressive large language models(LLMs) and multimodal large language models (MLLMs).
Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos
In the second stage, for each semantics, we randomly sample slots from the corresponding Gaussian distribution and perform masked feature aggregation within the semantic area to exploit temporal correspondence patterns for instance identification.
CLEVA: Chinese Language Models EVAluation Platform
With the continuous emergence of Chinese Large Language Models (LLMs), how to evaluate a model's capabilities has become an increasingly significant issue.
Learning Referring Video Object Segmentation from Weak Annotation
To relieve the burden of data annotation while maintaining sufficient supervision for segmentation, we propose a new annotation scheme, in which we label the frame where the object first appears with a mask and use bounding boxes for the subsequent frames.
Improving Pixel-based MIM by Reducing Wasted Modeling Capability
There has been significant progress in Masked Image Modeling (MIM).
DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering
Realistic human-centric rendering plays a key role in both computer vision and computer graphics.
MMBench: Is Your Multi-modal Model an All-around Player?
In response to these challenges, we propose MMBench, a novel multi-modality benchmark.
Ranked #1 on
Visual Question Answering
on MMBench
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
With the advance of text-to-image models (e. g., Stable Diffusion) and corresponding personalization techniques such as DreamBooth and LoRA, everyone can manifest their imagination into high-quality images at an affordable cost.
HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE
Factor model is a fundamental investment tool in quantitative investment, which can be empowered by deep learning to become more flexible and efficient in practical complicated investing situations.
E2EAI: End-to-End Deep Learning Framework for Active Investing
Active investing aims to construct a portfolio of assets that are believed to be relatively profitable in the markets, with one popular method being to construct a portfolio via factor-based strategies.
RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars
It is a large-scale digital library for head avatars with three key attributes: 1) High Fidelity: all subjects are captured by 60 synchronized, high-resolution 2K cameras in 360 degrees.
RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer
Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy.
V3Det: Vast Vocabulary Visual Detection Dataset
To facilitate the development of more general visual object detection, we propose V3Det, a vast vocabulary visual detection dataset with precisely annotated bounding boxes on massive images.
SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling
Synthetic data has emerged as a promising source for 3D human research as it offers low-cost access to large-scale human datasets.
DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking
Recent multi-camera 3D object detectors usually leverage temporal information to construct multi-view stereo that alleviates the ill-posed depth estimation.
Grid-guided Neural Radiance Fields for Large Urban Scenes
An alternative solution is to use a feature grid representation, which is computationally efficient and can naturally scale to a large scene with increased grid resolutions.
AssetField: Assets Mining and Reconfiguration in Ground Feature Plane Representation
Traditional modeling pipelines keep an asset library storing unique object templates, which is both versatile and memory efficient in practice.
MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
This paper introduces the Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training and a carefully designed data-efficient 3D object detection benchmark on the Waymo dataset.
Position-Guided Point Cloud Panoptic Segmentation Transformer
DEtection TRansformer (DETR) started a trend that uses a group of learnable queries for unified visual perception.
Ranked #1 on
Panoptic Segmentation
on SemanticKITTI
Controllable Mesh Generation Through Sparse Latent Point Diffusion Models
In this work, we design a novel sparse latent point diffusion model for mesh generation.
PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling
Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT.
Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Production
Amateurs working on mini-films and short-form videos usually spend lots of time and effort on the multi-round complicated process of setting and adjusting scenes, plots, and cameras to deliver satisfying video shots.
OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases.
Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant
Semi-Supervised Semantic Segmentation aims at training the segmentation model with limited labeled data and a large amount of unlabeled data.
SPTS v2: Single-Point Scene Text Spotting
Within the context of our SPTS v2 framework, our experiments suggest a potential preference for single-point representation in scene text spotting when compared to other representations.
Ranked #14 on
Text Spotting
on ICDAR 2015
Learning Human Dynamics in Autonomous Driving Scenarios
In this work, we propose a holistic framework for learning physically plausible human dynamics from real driving scenarios, narrowing the gap between real and simulated human behavior in safety-critical applications.
RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer
Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy.
Multi-Level Logit Distillation
Through this framework, the prediction alignment is not only conducted at the instance level, but also at the batch and class level, through which the student model learns instance prediction, input correlation, and category correlation simultaneously.
Audio-Driven Co-Speech Gesture Video Generation
Our key insight is that the co-speech gestures can be decomposed into common motion patterns and subtle rhythmic dynamics.
Factor Investing with a Deep Multi-Factor Model
Modeling and characterizing multiple factors is perhaps the most important step in achieving excess returns over market benchmarks.
Rethinking Trajectory Prediction via "Team Game"
To accurately predict trajectories in multi-agent settings, e. g. team games, it is important to effectively model the interactions among agents.
Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows
The ability to choose an appropriate camera view among multiple cameras plays a vital role in TV shows delivery.
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition
Graph convolution networks (GCN) have been widely used in skeleton-based action recognition.
Ranked #5 on
Skeleton Based Action Recognition
on NTU RGB+D
Force-Aware Interface via Electromyography for Natural VR/AR Interaction
Closing the gap between real-world physicality and immersive virtual experience requires a closed interaction loop: applying user-exerted physical forces to the virtual environment and generating haptic sensations back to the users.
Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks
Deep learning models have achieved excellent recognition results on large-scale video benchmarks.
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance.
Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training for a single scene.
OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images
More precisely, the OmniCity contains multi-view satellite images as well as street-level panorama and mono-view images, constituting over 100K pixel-wise annotated images that are well-aligned and collected from 25K geo-locations in New York City.
Monocular 3D Object Detection with Depth from Motion
Perceiving 3D objects from monocular inputs is crucial for robotic systems, given its economy compared to multi-sensor settings.
Static and Dynamic Concepts for Self-supervised Video Representation Learning
In this paper, we propose a novel learning scheme for self-supervised video representation learning.
Guided Diffusion Model for Adversarial Purification
In this paper, we propose a novel purification approach, referred to as guided diffusion model for purification (GDMP), to help protect classifiers from adversarial attacks.
Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis
The ability to synthesize long-term human motion sequences in real-world scenes can facilitate numerous applications.
Accelerating Diffusion Models via Early Stop of the Diffusion Process
By modeling the reverse process of gradually diffusing the data distribution into a Gaussian distribution, generating a sample in DDPMs can be regarded as iteratively denoising a randomly sampled Gaussian noise.
PYSKL: Towards Good Practices for Skeleton Action Recognition
The toolbox supports a wide variety of skeleton action recognition algorithms, including approaches based on GCN and CNN.
Ranked #15 on
Skeleton Based Action Recognition
on NTU RGB+D
MINI: Mining Implicit Novel Instances for Few-Shot Object Detection
The offline mining mechanism leverages a self-supervised discriminative model to collaboratively mine implicit novel instances with a trained FSOD network.
TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition
To mitigate this problem, we developed TransRank, a unified framework for recognizing Transformations in a Ranking formulation.
SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition
End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition.
Ranked #3 on
Text Spotting
on Inverse-Text
OCSampler: Compressing Videos to One Clip with Single-step Sampling
Recent works prefer to formulate frame sampling as a sequential decision task by selecting frames one by one according to their importance, while we present a new paradigm of learning instance-specific video condensation policies to select informative frames for representing the entire video only in a single step.
SPTS: Single-Point Text Spotting
For the first time, we demonstrate that training scene text spotting models can be achieved with an extremely low-cost annotation of a single-point for each instance.
Ranked #2 on
Text Spotting
on SCUT-CTW1500
BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering
The wide span of viewing positions within these scenes yields multi-scale renderings with very different levels of detail, which poses great challenges to neural radiance field and biases it towards compromised results.
A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion
The RFNet refines the coarse output of the CGNet and further improves quality of the completed point cloud.
Balanced Chamfer Distance as a Comprehensive Metric for Point Cloud Completion
We adopt DCD to evaluate the point cloud completion task, where experimental results show that DCD pays attention to both the overall structure and local geometric details and provides a more reliable evaluation even when CD and EMD contradict each other.
Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion
We adopt DCD to evaluate the point cloud completion task, where experimental results show that DCD pays attention to both the overall structure and local geometric details and provides a more reliable evaluation even when CD and EMD contradict each other.
Few-Shot Object Detection via Association and DIscrimination
1) In the association step, in contrast to implicitly leveraging multiple base classes, we construct a compact novel class feature space via explicitly imitating a specific base class feature space.
INTERN: A New Learning Paradigm Towards General Vision
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society.
Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
In this paper, we propose Generative Occupancy Fields (GOF), a novel model based on generative radiance fields that can learn compact object surfaces without impeding its training convergence.
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception
In this paper, we benchmark our model on these three tasks.
Temporal RoI Align for Video Object Recognition
In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity.
Ranked #1 on
Video Instance Segmentation
on YouTube-VIS
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.
MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding
We present MMOCR-an open-source toolbox which provides a comprehensive pipeline for text detection and recognition, as well as their downstream tasks such as named entity recognition and key information extraction.
Vision Transformer with Progressive Sampling
As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image classification, by simply splitting images into tokens with a fixed length, and employing transformers to learn relations between these tokens.
Probabilistic and Geometric Depth: Detecting Objects in Perspective
As the preliminary depth estimation of each instance is usually inaccurate in this ill-posed setting, we incorporate a probabilistic representation to capture the uncertainty.
Ranked #10 on
3D Object Detection
on KITTI Cars Hard val
Transcript to Video: Efficient Clip Sequencing from Texts
To meet the demands for non-experts, we present Transcript-to-Video -- a weakly-supervised framework that uses texts as input to automatically create video sequences from an extensive collection of shots.
Scene-aware Generative Network for Human Motion Synthesis
We revisit human motion synthesis, a task useful in various real world applications, in this paper.
WSSOD: A New Pipeline for Weakly- and Semi-Supervised Object Detection
The performance of object detection, to a great extent, depends on the availability of large annotated datasets.
Revisiting Skeleton-based Action Recognition
In this work, we propose PoseC3D, a new approach to skeleton-based action recognition, which relies on a 3D heatmap stack instead of a graph sequence as the base representation of human skeletons.
Ranked #1 on
Action Recognition
on Volleyball
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
In this paper, we study this problem with a practice built on a fully convolutional single-stage detector and propose a general framework FCOS3D.
Ranked #320 on
3D Object Detection
on nuScenes
Visually Informed Binaural Audio Generation without Binaural Audios
Moreover, combined with binaural recordings, our method is able to further boost the performance of binaural audio generation under supervised settings.
Adversarial Robustness under Long-Tailed Distribution
We then perform a systematic study on existing long-tailed recognition methods in conjunction with the adversarial training framework.
Towards Evaluating and Training Verifiably Robust Neural Networks
Recent works have shown that interval bound propagation (IBP) can be used to train verifiably robust neural networks.
3D Building Reconstruction From Monocular Remote Sensing Images
3D building reconstruction from monocular remote sensing imagery is an important research problem and an economic solution to large-scale city modeling, compared with reconstruction from LiDAR data and multi-view imagery.
BlockPlanner: City Block Generation With Vectorized Graph Representation
City modeling is the foundation for computational urban planning, navigation, and entertainment.
CARAFE++: Unified Content-Aware ReAssembly of FEatures
Feature reassembly, i. e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e. g., residual networks and feature pyramids.
FLAVA: Find, Localize, Adjust and Verify to Annotate LiDAR-Based Point Clouds
Recent years have witnessed the rapid progress of perception algorithms on top of LiDAR, a widely adopted sensor for autonomous driving systems.
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited.
Ranked #2 on
3D Semantic Segmentation
on ScribbleKITTI
Understanding the wiring evolution in differentiable neural architecture search
To this end, we pose questions that future differentiable methods for neural wiring discovery need to confront, hoping to evoke a discussion and rethinking on how much bias has been enforced implicitly in existing NAS methods.
Seesaw Loss for Long-Tailed Instance Segmentation
Instances of head classes dominate a long-tailed dataset and they serve as negative samples of tail categories.
Online Multi-modal Person Search in Videos
The task of searching certain people in videos has seen increasing potential in real-world applications, such as video organization and editing.
A Unified Framework for Shot Type Classification Based on Subject Centric Lens
Shots are key narrative elements of various videos, e. g. movies, TV series, and user-generated videos that are thriving over the Internet.
Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation
A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space.
Ranked #9 on
LIDAR Semantic Segmentation
on nuScenes
MovieNet: A Holistic Dataset for Movie Understanding
We believe that such a holistic dataset would promote the researches on story-based long video understanding and beyond.
Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation
Stereophonic audio is an indispensable ingredient to enhance human auditory experience.
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions.
Ranked #7 on
Long-tail Learning
on VOC-MLT
Learn to Propagate Reliably on Noisy Affinity Graphs
Recent works have shown that exploiting unlabeled data through label propagation can substantially reduce the labeling cost, which has been a critical issue in developing visual recognition models.
Placepedia: Comprehensive Place Understanding with Multi-Faceted Annotations
Place is an important element in visual understanding.
Novel Policy Seeking with Constrained Optimization
In problem-solving, we humans can come up with multiple novel solutions to the same problem.
Intra- and Inter-Action Understanding via Temporal Action Parsing
Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features.
Motion Guided 3D Pose Estimation from Videos
We propose a new loss function, called motion loss, for the problem of monocular 3D Human pose estimation from 2D pose.
Ranked #17 on
3D Human Pose Estimation
on Human3.6M
Evolutionary Stochastic Policy Distillation
Solving the Goal-Conditioned Reward Sparse (GCRS) task is a challenging reinforcement learning problem due to the sparsity of reward signals.
FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding
To take action recognition to a new level, we develop FineGym, a new dataset built on top of gymnastic videos.
Feature Pyramid Grids
Feature pyramid networks have been widely adopted in the object detection literature to improve feature representations for better handling of variations in scale.
A Local-to-Global Approach to Multi-modal Movie Scene Segmentation
Scene, as the crucial unit of storytelling in movies, contains complex activities of actors and their interactions in a physical environment.
Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds
LiDAR is an important method for autonomous driving systems to sense the environment.
Self-Supervised Scene De-occlusion
This is achieved via Partial Completion Network (PCNet)-mask (M) and -content (C), that learn to recover fractions of object masks and contents, respectively, in a self-supervised manner.
SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
Multi-class 3D object detection aims to localize and classify objects of multiple categories from point clouds.
Learning to Cluster Faces via Confidence and Connectivity Estimation
With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters.
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Learning a good image prior is a long-term goal for image restoration and manipulation.
Omni-sourced Webly-supervised Learning for Video Recognition
Then a joint-training strategy is proposed to deal with the domain gaps between multiple data sources and formats in webly-supervised learning.
Ranked #4 on
Action Recognition
on UCF101
(using extra training data)
Learning Diverse Fashion Collocation by Neural Graph Filtering
To facilitate a comprehensive study on diverse fashion collocation, we reorganize Amazon Fashion dataset with carefully designed evaluation protocols.
DSNAS: Direct Neural Architecture Search without Parameter Retraining
We argue that given a computer vision task for which a NAS method is expected, this definition can reduce the vaguely-defined NAS evaluation to i) accuracy of this task and ii) the total computation consumed to finally obtain a model with satisfying accuracy.
Ranked #15 on
Neural Architecture Search
on NAS-Bench-201, ImageNet-16-120
(Accuracy (Val) metric)
Real or Not Real, that is the Question
While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles.
Regularizing Reasons for Outfit Evaluation with Gradient Penalty
In this paper, we build an outfit evaluation system which provides feedbacks consisting of a judgment with a convincing explanation.
Side-Aware Boundary Localization for More Precise Object Detection
To tackle the difficulty of precise localization in the presence of displacements with large variance, we further propose a two-step localization scheme, which first predicts a range of movement through bucket prediction and then pinpoints the precise position within the predicted bucket.
Fastened CROWN: Tightened Neural Network Robustness Certificates
We draw inspiration from such work and further demonstrate the optimality of deterministic CROWN (Zhang et al. 2018) solutions in a given linear programming problem under mild constraints.
Learning a Decision Module by Imitating Driver's Control Behaviors
In this work, we propose a hybrid framework to learn neural decisions in the classical modular pipeline through end-to-end imitation learning.
When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks
Recent advances in adversarial attacks uncover the intrinsic vulnerability of modern deep neural networks.
Learning to Synthesize Fashion Textures
Another important observation is that fashion textures are multi-modal.
Policy Continuation with Hindsight Inverse Dynamics
This approach learns from Hindsight Inverse Dynamics based on Hindsight Experience Replay, enabling the learning process in a self-imitated manner and thus can be trained with supervised learning.
A Graph-Based Framework to Bridge Movies and Synopses
On top of this dataset, we develop a framework to perform matching between movie segments and synopsis paragraphs.
Regulatory Focus: Promotion and Prevention Inclinations in Policy Search
The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths.
Learning with Social Influence through Interior Policy Differentiation
In this work we model the social influence into the scheme of reinforcement learning, enabling the agents to learn both from the environment and from their peers.
Biased Estimates of Advantages over Path Ensembles
The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths.
Open Compound Domain Adaptation
A typical domain adaptation approach is to adapt models trained on the annotated data in a source domain (e. g., sunny weather) for achieving high performance on the test data in a target domain (e. g., rainy weather).
Recursive Visual Sound Separation Using Minus-Plus Net
Sounds provide rich semantics, complementary to visual data, for many tasks.
MMDetection: Open MMLab Detection Toolbox and Benchmark
In this paper, we introduce the various features of this toolbox.
POPQORN: Quantifying Robustness of Recurrent Neural Networks
The vulnerability to adversarial attacks has been a critical issue for deep neural networks.
Online Hyper-parameter Learning for Auto-Augmentation Strategy
Data augmentation is critical to the success of modern deep learning techniques.
CARAFE: Content-Aware ReAssembly of FEatures
CARAFE introduces little computational overhead and can be readily integrated into modern network architectures.
Prime Sample Attention in Object Detection
Our experiments demonstrate that it is often more effective to focus on prime samples than hard samples when training a detector.
Learning to Cluster Faces on an Affinity Graph
Face recognition sees remarkable progress in recent years, and its performance has reached a very high level.
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 #163 on
Object Detection
on COCO test-dev
Self-Supervised Learning via Conditional Motion Propagation
Instead of explicitly modeling the motion probabilities, we design the pretext task as a conditional motion propagation problem.
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
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 #33 on
Object Detection
on COCO-O
Region Proposal by Guided Anchoring
State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and aspect ratios.
Ranked #1 on
Region Proposal
on COCO test-dev
Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis
For recovering 3D object poses from 2D images, a prevalent method is to pre-train an over-complete dictionary $\mathcal D=\{B_i\}_i^D$ of 3D basis poses.
IRLAS: Inverse Reinforcement Learning for Architecture Search
Motivated by the fact that human-designed networks are elegant in topology with a fast inference speed, we propose a mirror stimuli function inspired by biological cognition theory to extract the abstract topological knowledge of an expert human-design network (ResNeXt).
An Embarrassingly Simple Approach for Knowledge Distillation
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model.
Trajectory Convolution for Action Recognition
How to leverage the temporal dimension is a key question in video analysis.
A Neural Compositional Paradigm for Image Captioning
Mainstream captioning models often follow a sequential structure to generate captions, leading to issues such as introduction of irrelevant semantics, lack of diversity in the generated captions, and inadequate generalization performance.
Improving On-policy Learning with Statistical Reward Accumulation
Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted cumulative returns.
Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition
Face recognition has witnessed great progress in recent years, mainly attributed to the high-capacity model designed and the abundant labeled data collected.
Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
Due to the expensive and time-consuming annotations (e. g., segmentation) for real-world images, recent works in computer vision resort to synthetic data.
PSANet: Point-wise Spatial Attention Network for Scene Parsing
We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes.
Ranked #47 on
Semantic Segmentation
on Cityscapes test
Lifelong Learning via Progressive Distillation and Retrospection
Lifelong learning aims at adapting a learned model to new tasks while retaining the knowledge gained earlier.
Find and Focus: Retrieve and Localize Video Events with Natural Language Queries
The thriving of video sharing services brings new challenges to video retrieval, e. g. the rapid growth in video duration and content diversity.
Generative Adversarial Frontal View to Bird View Synthesis
Due to the large gap and severe deformation between the frontal view and bird view, generating a bird view image from a single frontal view is challenging.
Pose Guided Human Video Generation
Human pose, on the other hand, can represent motion patterns intrinsically and interpretably, and impose the geometric constraints regardless of appearance.
Person Search in Videos with One Portrait Through Visual and Temporal Links
In real-world applications, e. g. law enforcement and video retrieval, one often needs to search a certain person in long videos with just one portrait.
Move Forward and Tell: A Progressive Generator of Video Descriptions
We present an efficient framework that can generate a coherent paragraph to describe a given video.
Rethinking the Form of Latent States in Image Captioning
Taking advantage of this, we visually reveal the internal dynamics in the process of caption generation, as well as the connections between input visual domain and output linguistic domain.
Probabilistic Ensemble of Collaborative Filters
Collaborative filtering is an important technique for recommendation.
From Trailers to Storylines: An Efficient Way to Learn from Movies
Experiments on this dataset showed that the proposed method can substantially reduce the training time while obtaining highly effective features and coherent temporal structures.
Unifying Identification and Context Learning for Person Recognition
In this work, we aim to move beyond such limitations and propose a new framework to leverage context for person recognition.
Unsupervised Feature Learning via Non-Parametric Instance Discrimination
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so.
Ranked #38 on
Semi-Supervised Image Classification
on ImageNet - 1% labeled data
(Top 5 Accuracy metric)
Recognize Actions by Disentangling Components of Dynamics
Despite the remarkable progress in action recognition over the past several years, existing methods remain limited in efficiency and effectiveness.
Learning Globally Optimized Object Detector via Policy Gradient
In this paper, we propose a simple yet effective method to learn globally optimized detector for object detection, which is a simple modification to the standard cross-entropy gradient inspired by the REINFORCE algorithm.
Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so.
Ranked #13 on
Contrastive Learning
on imagenet-1k