Search Results for author:
Found 410 papers, 245 papers with code
Motionlets: Mid-level 3D Parts for Human Motion Recognition
We postulate three key properties of motionlet for action recognition: high motion saliency, multiple scale representation, and representative-discriminative ability.
A Study on Unsupervised Dictionary Learning and Feature Encoding for Action Classification
Many efforts have been devoted to develop alternative methods to traditional vector quantization in image domain such as sparse coding and soft-assignment.
Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice
Many efforts have been made in each step independently in different scenarios and their effect on action recognition is still unknown.
Multi-View Super Vector for Action Recognition
Kernel average is then applied on these components to produce recognition result.
Object-Scene Convolutional Neural Networks for Event Recognition in Images
Meanwhile, we investigate different network architectures for OS-CNN design, and adapt the deep (AlexNet) and very-deep (GoogLeNet) networks to the task of event recognition.
Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
Visual features are of vital importance for human action understanding in videos.
Ranked #59 on
Action Recognition
on HMDB-51
Boosting Optical Character Recognition: A Super-Resolution Approach
Text image super-resolution is a challenging yet open research problem in the computer vision community.
Reading Scene Text in Deep Convolutional Sequences
We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem.
Towards Good Practices for Very Deep Two-Stream ConvNets
However, for action recognition in videos, the improvement of deep convolutional networks is not so evident.
Ranked #66 on
Action Recognition
on UCF101
Local Color Contrastive Descriptor for Image Classification
Our descriptor enriches local image representation with both color and contrast information.
Places205-VGGNet Models for Scene Recognition
We verify the performance of trained Places205-VGGNet models on three datasets: MIT67, SUN397, and Places205.
Local Multi-Grouped Binary Descriptor with Ring-based Pooling Configuration and Optimization
The performance of RMGD was evaluated on a number of publicly available benchmarks, where the RMGD outperforms the state-of-the-art binary descriptors significantly.
Text-Attentional Convolutional Neural Networks for Scene Text Detection
The rich supervision information enables the Text-CNN with a strong capability for discriminating ambiguous texts, and also increases its robustness against complicated background components.
Better Exploiting OS-CNNs for Better Event Recognition in Images
Event recognition from still images is one of the most important problems for image understanding.
Locally-Supervised Deep Hybrid Model for Scene Recognition
Secondly, we propose a new Local Convolutional Supervision (LCS) layer to enhance the local structure of the image by directly propagating the label information to the convolutional layers.
Text-attentional convolutional neural network for scene text detection
Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images.
Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
We propose a novel Cascaded Convolutional Text Network (CCTN) that joints two customized convolutional networks for coarse-to-fine text localization.
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations and occlusions.
Ranked #27 on
Face Detection
on WIDER Face (Easy)
Actionness Estimation Using Hybrid Fully Convolutional Networks
Actionness was introduced to quantify the likelihood of containing a generic action instance at a specific location.
Ranked #11 on
Action Detection
on J-HMDB
Real-time Action Recognition with Enhanced Motion Vector CNNs
The deep two-stream architecture exhibited excellent performance on video based action recognition.
Ranked #74 on
Action Recognition
on UCF101
Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition
In order to address this problem, we propose a novel deep face recognition framework to learn the age-invariant deep face features through a carefully designed CNN model.
Ranked #7 on
Age-Invariant Face Recognition
on CACDVS
A Key Volume Mining Deep Framework for Action Recognition
Training with a large proportion of irrelevant volumes will hurt performance.
DeepWriter: A Multi-Stream Deep CNN for Text-independent Writer Identification
The main contributions are: 1) we design and optimize multi-stream structure for writer identification task; 2) we introduce data augmentation learning to enhance the performance of DeepWriter; 3) we introduce a patch scanning strategy to handle text image with different lengths.
CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016
This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016.
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network.
Ranked #3 on
Multimodal Activity Recognition
on EV-Action
Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images
These newly designed transferring techniques exploit multi-task learning frameworks to incorporate extra knowledge from other networks and additional datasets into the training procedure of event CNNs.
Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition
In this paper, we propose a hybrid representation, which leverages the discriminative capacity of CNNs and the simplicity of descriptor encoding schema for image recognition, with a focus on scene recognition.
Detecting Text in Natural Image with Connectionist Text Proposal Network
We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image.
A Discriminative Feature Learning Approach for Deep Face Recognition
In most of the available CNNs, the softmax loss function is used as the supervision signal to train the deep model.
Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs
Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2.
Range Loss for Deep Face Recognition with Long-tail
Convolutional neural networks have achieved great improvement on face recognition in recent years because of its extraordinary ability in learning discriminative features of people with different identities.
Temporal Segment Networks for Action Recognition in Videos
Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.
Ranked #5 on
Video Classification
on COIN
Single Shot Text Detector with Regional Attention
Our text detector achieves an F-measure of 77% on the ICDAR 2015 bench- mark, advancing the state-of-the-art results in [18, 28].
Ranked #4 on
Scene Text Detection
on COCO-Text
Deep Embedding Convolutional Neural Network for Synthesizing CT Image from T1-Weighted MR Image
After repeat-ing this embedding procedure for several times in the network, we can eventually synthesize a final CT image in the end of the DECNN.
Detecting Faces Using Inside Cascaded Contextual CNN
Deep Convolutional Neural Networks (CNNs) achieve substantial improvements in face detection in the wild.
Range Loss for Deep Face Recognition With Long-Tailed Training Data
Unlike these work, this paper investigated how long-tailed data impact the training of face CNNs and develop a novel loss function, called range loss, to effectively utilize the tailed data in training process.
RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos
Firstly, unlike previous works on pose-related action recognition, our RPAN is an end-to-end recurrent network which can exploit important spatial-temporal evolutions of human pose to assist action recognition in a unified framework.
Ranked #5 on
Skeleton Based Action Recognition
on J-HMDB
Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward
Video summarization aims to facilitate large-scale video browsing by producing short, concise summaries that are diverse and representative of original videos.
Ranked #7 on
Unsupervised Video Summarization
on TvSum
FOTS: Fast Oriented Text Spotting with a Unified Network
Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community.
Ranked #4 on
Scene Text Detection
on ICDAR 2017 MLT
Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering
Visual question answering (VQA) is of significant interest due to its potential to be a strong test of image understanding systems and to probe the connection between language and vision.
LSTD: A Low-Shot Transfer Detector for Object Detection
Second, we introduce a novel regularized transfer learning framework for low-shot detection, where the transfer knowledge (TK) and background depression (BD) regularizations are proposed to leverage object knowledge respectively from source and target domains, in order to further enhance fine-tuning with a few target images.
Ranked #22 on
Few-Shot Object Detection
on MS-COCO (30-shot)
An end-to-end TextSpotter with Explicit Alignment and Attention
This allows the two tasks to work collaboratively by shar- ing convolutional features, which is critical to identify challenging text instances.
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds.
Ranked #6 on
3D Part Segmentation
on IntrA
Boosting up Scene Text Detectors with Guided CNN
Deep CNNs have achieved great success in text detection.
Knowledge-based Fully Convolutional Network and Its Application in Segmentation of Lung CT Images
A variety of deep neural networks have been applied in medical image segmentation and achieve good performance.
Temporal Hallucinating for Action Recognition With Few Still Images
To mimic this capacity, we propose a novel Hybrid Video Memory (HVM) machine, which can hallucinate temporal features of still images from video memory, in order to boost action recognition with few still images.
Prostate Segmentation using 2D Bridged U-net
To address the aforementioned three problems, we propose and validate a deeper network that can fit medical image datasets that are usually small in the sample size.
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN).
Ranked #2 on
Face Hallucination
on FFHQ 512 x 512 - 16x upscaling
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.
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones.
Super-Identity Convolutional Neural Network for Face Hallucination
Face hallucination is a generative task to super-resolve the facial image with low resolution while human perception of face heavily relies on identity information.
Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers
In image restoration tasks, like denoising and super resolution, continual modulation of restoration levels is of great importance for real-world applications, but has failed most of existing deep learning based image restoration methods.
Ranked #2 on
Color Image Denoising
on CBSD68 sigma75
AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
Our results show that training deep neural networks with the AdaCos loss is stable and able to achieve high face recognition accuracy.
Ranked #6 on
Face Verification
on MegaFace
P2SGrad: Refined Gradients for Optimizing Deep Face Models
Cosine-based softmax losses significantly improve the performance of deep face recognition networks.
Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition
Extensive experiments show that our RAN and region biased loss largely improve the performance of FER with occlusion and variant pose.
Ranked #2 on
Facial Expression Recognition (FER)
on SFEW
Facial Expression Recognition
Facial Expression Recognition (FER)
Suppressing Model Overfitting for Image Super-Resolution Networks
Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved.
Frame attention networks for facial expression recognition in videos
The feature embedding module is a deep Convolutional Neural Network (CNN) which embeds face images into feature vectors.
Ranked #3 on
Facial Expression Recognition (FER)
on CK+
(Accuracy (7 emotion) metric)
Facial Expression Recognition
Facial Expression Recognition (FER)
Bootstrap Model Ensemble and Rank Loss for Engagement Intensity Regression
Based on our winner solution last year, we mainly explore head features and body features with a bootstrap strategy and two novel loss functions in this paper.
Product Image Recognition with Guidance Learning and Noisy Supervision
Instead of collecting product images by labor-and time-intensive image capturing, we take advantage of the web and download images from the reviews of several e-commerce websites where the images are casually captured by consumers.
RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution
To address the problem, we propose Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize generator in the direction of perceptual metrics.
Ranked #1 on
Image Super-Resolution
on PIRM-test
Learning Category Correlations for Multi-label Image Recognition with Graph Networks
In this paper, instead of using a pre-defined graph which is inflexible and may be sub-optimal for multi-label classification, we propose the A-GCN, which leverages the popular Graph Convolutional Networks with an Adaptive label correlation graph to model label dependencies.
Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration
To make a step forward, this paper presents a new problem setup, called multi-dimension (MD) modulation, which aims at modulating output effects across multiple degradation types and levels.
Geometry Sharing Network for 3D Point Cloud Classification and Segmentation
Specially, GS-Net consists of Geometry Similarity Connection (GSC) modules which exploit Eigen-Graph to group distant points with similar and relevant geometric information, and aggregate features from nearest neighbors in both Euclidean space and Eigenvalue space.
Ranked #7 on
3D Point Cloud Classification
on IntrA
Pose-Assisted Multi-Camera Collaboration for Active Object Tracking
In the system, each camera is equipped with two controllers and a switcher: The vision-based controller tracks targets based on observed images.
FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing
With the proposed Fusion-discriminator which takes frequency information as additional priors, our model can generator more natural and realistic dehazed images with less color distortion and fewer artifacts.
A Comprehensive Study on Temporal Modeling for Online Action Detection
Online action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years.
Progressive Object Transfer Detection
Inspired by this procedure of learning to detect, we propose a novel Progressive Object Transfer Detection (POTD) framework.
Learning Attentive Pairwise Interaction for Fine-Grained Classification
These distinct gate vectors inherit mutual context on semantic differences, which allow API-Net to attentively capture contrastive clues by pairwise interaction between two images.
Ranked #12 on
Fine-Grained Image Classification
on Stanford Dogs
Suppressing Uncertainties for Large-Scale Facial Expression Recognition
Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators.
Facial Expression Recognition
Facial Expression Recognition (FER)
Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units
Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e. g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states).
TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation
Video action anticipation aims to predict future action categories from observed frames.
Context-Transformer: Tackling Object Confusion for Few-Shot Detection
Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors.
Domain Adaptive Ensemble Learning
Each such classifier is an expert to its own domain and a non-expert to others.
Learning to Predict Context-adaptive Convolution for Semantic Segmentation
Long-range contextual information is essential for achieving high-performance semantic segmentation.
Understanding the Dynamics of Second Language Writing through Keystroke Logging and Complexity Contours
The purpose of this paper is twofold: [1] to introduce, to our knowledge, the largest available resource of keystroke logging (KSL) data generated by Etherpad (https://etherpad. org/), an open-source, web-based collaborative real-time editor, that captures the dynamics of second language (L2) production and [2] to relate the behavioral data from KSL to indices of syntactic and lexical complexity of the texts produced obtained from a tool that implements a sliding window approach capturing the progression of complexity within a text.
COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named ClOthes ChAnging Person Set (COCAS), which provides multiple images of the same identity with different clothes.
Attention-Guided Hierarchical Structure Aggregation for Image Matting
In this paper, we propose an end-to-end Hierarchical Attention Matting Network (HAttMatting), which can predict the better structure of alpha mattes from single RGB images without additional input.
Ranked #6 on
Image Matting
on P3M-10k
SmallBigNet: Integrating Core and Contextual Views for Video Classification
Our SmallBig network outperforms a number of recent state-of-the-art approaches, in terms of accuracy and/or efficiency.
Becoming Linguistically Mature: Modeling English and German Children's Writing Development Across School Grades
In this paper we employ a novel approach to advancing our understanding of the development of writing in English and German children across school grades using classification tasks.
Visual Compositional Learning for Human-Object Interaction Detection
The integration of decomposition and composition enables VCL to share object and verb features among different HOI samples and images, and to generate new interaction samples and new types of HOI, and thus largely alleviates the long-tail distribution problem and benefits low-shot or zero-shot HOI detection.
Ranked #3 on
Affordance Recognition
on HICO-DET(Unknown Concepts)
Exploring Multi-Scale Feature Propagation and Communication for Image Super Resolution
Multi-scale techniques have achieved great success in a wide range of computer vision tasks.
Enhanced Quadratic Video Interpolation
In this work, we further improve the performance of QVI from three facets and propose an enhanced quadratic video interpolation (EQVI) model.
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
In this paper, we present BSN++, a new framework which exploits complementary boundary regressor and relation modeling for temporal proposal generation.
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
Second, the parameter frequency distribution is further adopted to guide the student network to learn the appearance modeling process from the teacher.
Conditional Sequential Modulation for Efficient Global Image Retouching
The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector.
Efficient Image Super-Resolution Using Pixel Attention
Pixel attention (PA) is similar as channel attention and spatial attention in formulation.
Suppressing Mislabeled Data via Grouping and Self-Attention
Specifically, this plug-and-play AFM first leverages a \textit{group-to-attend} module to construct groups and assign attention weights for group-wise samples, and then uses a \textit{mixup} module with the attention weights to interpolate massive noisy-suppressed samples.
Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition
To this end, we propose an Attention-Driven Dynamic Graph Convolutional Network (ADD-GCN) to dynamically generate a specific graph for each image.
Ranked #22 on
Multi-Label Classification
on MS-COCO
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud
GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components.
Ranked #1 on
Point Cloud Segmentation
on PointCloud-C
Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition
The audio-video based emotion recognition aims to classify a given video into basic emotions.
Facial Expression Recognition (FER)
Video Emotion Recognition
Tripartite Information Mining and Integration for Image Matting
Regarding the nature of image matting, most researches have focused on solutions for transition regions.
Multi-scale Information Assembly for Image Matting
Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images.
Domain Generalization: A Survey
Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce.
Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering
The multi-label learning module leverages a memory feature bank and assigns each image with a multi-label vector based on the similarities between the image and feature bank.
Detecting Human-Object Interaction via Fabricated Compositional Learning
With the proposed object fabricator, we are able to generate large-scale HOI samples for rare and unseen categories to alleviate the open long-tailed issues in HOI detection.
Ranked #4 on
Affordance Recognition
on HICO-DET
PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos
By coupling advanced 3D pose estimators and HMR in a serial or parallel manner, these two frameworks can effectively correct human mesh with guidance of a concise pose calibration module.
Ranked #4 on
3D Human Pose Estimation
on Surreal
Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud
This paper investigates the indistinguishable points (difficult to predict label) in semantic segmentation for large-scale 3D point clouds.
Temporal Context Aggregation Network for Temporal Action Proposal Refinement
In this paper, we propose Temporal Context Aggregation Network (TCANet) to generate high-quality action proposals through "local and global" temporal context aggregation and complementary as well as progressive boundary refinement.
Ranked #9 on
Temporal Action Localization
on ActivityNet-1.3
Smart Scribbles for Image Mating
Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles.
Domain Generalization with MixStyle
Our method, termed MixStyle, is motivated by the observation that visual domain is closely related to image style (e. g., photo vs.~sketch images).
Ranked #57 on
Domain Generalization
on PACS
Affordance Transfer Learning for Human-Object Interaction Detection
The proposed method can thus be used to 1) improve the performance of HOI detection, especially for the HOIs with unseen objects; and 2) infer the affordances of novel objects.
Ranked #2 on
Affordance Recognition
on HICO-DET(Unknown Concepts)
Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation
Recent studies have witnessed that self-supervised methods based on view synthesis obtain clear progress on multi-view stereo (MVS).
Very Lightweight Photo Retouching Network with Conditional Sequential Modulation
In practice, photo retouching can be accomplished by a series of image processing operations.
The Impact of ASR on the Automatic Analysis of Linguistic Complexity and Sophistication in Spontaneous L2 Speech
In recent years, automated approaches to assessing linguistic complexity in second language (L2) writing have made significant progress in gauging learner performance, predicting human ratings of the quality of learner productions, and benchmarking L2 development.
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021.
Neighbourhood-guided Feature Reconstruction for Occluded Person Re-Identification
Person images captured by surveillance cameras are often occluded by various obstacles, which lead to defective feature representation and harm person re-identification (Re-ID) performance.
FineAction: A Fine-Grained Video Dataset for Temporal Action Localization
Temporal action localization (TAL) is an important and challenging problem in video understanding.
Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
In UDCL, a universal expert supervises the learning of domain experts and continuously gathers knowledge from all domain experts.
HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization
In this work, we propose a novel learning-based approach using a spatially dynamic encoder-decoder network, HDRUNet, to learn an end-to-end mapping for single image HDR reconstruction with denoising and dequantization.
TSI: Temporal Saliency Integration for Video Action Recognition
Specifically, SME aims to highlight the motion-sensitive area through local-global motion modeling, where the saliency alignment and pyramidal feature difference are conducted successively between neighboring frames to capture motion dynamics with less noises caused by misaligned background.
CT-Net: Channel Tensorization Network for Video Classification
It can learn to exploit spatial, temporal and channel attention in a high-dimensional manner, to improve the cooperative power of all the feature dimensions in our CT-Module.
Ranked #18 on
Action Recognition
on Something-Something V1
Scalable Transformers for Neural Machine Translation
In this paper, we propose a novel Scalable Transformers, which naturally contains sub-Transformers of different scales and have shared parameters.
Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
Unsupervised object re-identification targets at learning discriminative representations for object retrieval without any annotations.
Alzheimer's Disease Detection from Spontaneous Speech through Combining Linguistic Complexity and (Dis)Fluency Features with Pretrained Language Models
In this paper, we combined linguistic complexity and (dis)fluency features with pretrained language models for the task of Alzheimer's disease detection of the 2021 ADReSSo (Alzheimer's Dementia Recognition through Spontaneous Speech) challenge.
Prior-Induced Information Alignment for Image Matting
Image matting is an ill-posed problem that aims to estimate the opacity of foreground pixels in an image.
MixStyle Neural Networks for Domain Generalization and Adaptation
MixStyle is easy to implement with a few lines of code, does not require modification to training objectives, and can fit a variety of learning paradigms including supervised domain generalization, semi-supervised domain generalization, and unsupervised domain adaptation.
Blind Image Super-Resolution: A Survey and Beyond
This paper serves as a systematic review on recent progress in blind image SR, and proposes a taxonomy to categorize existing methods into three different classes according to their ways of degradation modelling and the data used for solving the SR model.
RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank
To address the problem, we propose Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize generator in the direction of different perceptual metrics.
Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
This technical report presents an overview of our solution used in the submission to 2021 HACS Temporal Action Localization Challenge on both Supervised Learning Track and Weakly-Supervised Learning Track.
Discovering Distinctive "Semantics" in Super-Resolution Networks
We show that a well-trained deep SR network is naturally a good descriptor of degradation information.
A New Journey from SDRTV to HDRTV
However, most available resources are still in standard dynamic range (SDR).
Digging into Uncertainty in Self-supervised Multi-view Stereo
Specially, the limitations can be categorized into two types: ambiguious supervision in foreground and invalid supervision in background.
Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
Graph Convolution Network (GCN) has been successfully used for 3D human pose estimation in videos.
Ranked #10 on
3D Human Pose Estimation
on HumanEva-I
A Novel Hybrid Convolutional Neural Network for Accurate Organ Segmentation in 3D Head and Neck CT Images
An essential step of RT planning is the accurate segmentation of various organs-at-risks (OARs) in HaN CT images.
Group Shift Pointwise Convolution for Volumetric Medical Image Segmentation
Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images.
UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning
For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60. 8% and 71. 4% top-1 accuracy respectively.
Ranked #8 on
Action Recognition
on Something-Something V1
Self-Slimming Vision Transformer
Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.
Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning
We address this problem from a new perspective, by jointly considering colorization and temporal consistency in a unified framework.
CLIP-Adapter: Better Vision-Language Models with Feature Adapters
Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning.
Estimating IRI based on pavement distress type, density, and severity: Insights from machine learning techniques
However, it is costly to measure IRI, and for this reason, certain road classes are excluded from IRI measurements at a network level.
Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
To further enhance CLIP's few-shot capability, CLIP-Adapter proposed to fine-tune a lightweight residual feature adapter and significantly improves the performance for few-shot classification.
Prediction of Listener Perception of Argumentative Speech in a Crowdsourced Dataset Using (Psycho-)Linguistic and Fluency Features
One of the key communicative competencies is the ability to maintain fluency in monologic speech and the ability to produce sophisticated language to argue a position convincingly.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
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.
MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning
With such multi-dimension and multi-scale factorization, our MorphMLP block can achieve a great accuracy-computation balance.
Ranked #38 on
Action Recognition
on Something-Something V2
(using extra training data)
Self-slimmed Vision Transformer
Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
Deep learning-based models encounter challenges when processing long-tailed data in the real world.
Ranked #2 on
Long-tail Learning
on iNaturalist 2018
(using extra training data)
A Simple Long-Tailed Recognition Baseline via Vision-Language Model
Recent advances in large-scale contrastive visual-language pretraining shed light on a new pathway for visual recognition.
Ranked #4 on
Long-tail Learning
on Places-LT
(using extra training data)
PointCLIP: Point Cloud Understanding by CLIP
On top of that, we design an inter-view adapter to better extract the global feature and adaptively fuse the few-shot knowledge learned from 3D into CLIP pre-trained in 2D.
Ranked #3 on
3D Open-Vocabulary Instance Segmentation
on STPLS3D
3D Open-Vocabulary Instance Segmentation
Few-Shot Learning
+6
CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation
Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations.
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
Reflash Dropout in Image Super-Resolution
Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR).
UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning
For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60. 9% and 71. 2% top-1 accuracy respectively.
CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning
To fill this gap, we propose a generic Contour-Perturbed Reconstruction Network (CP-Net), which can effectively guide self-supervised reconstruction to learn semantic content in the point cloud, and thus promote discriminative power of point cloud representation.
UniFormer: Unifying Convolution and Self-attention for Visual Recognition
Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing to tackle both redundancy and dependency for efficient and effective representation learning.
Ranked #153 on
Image Classification
on ImageNet
Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning
Especially, we develop a variant of ViT for 3D point cloud feature extraction, which also achieves comparable results with existing backbones when combined with our framework, and visualization of the attention maps show that our model does understand the point cloud by combining the global shape information and multiple local structural information, which is consistent with the inspiration of our representation learning method.
Hilbert Flattening: a Locality-Preserving Matrix Unfolding Method for Visual Discrimination
Flattening is essential in computer vision by converting multi-dimensional feature maps or images into one-dimensional vectors.
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
This work thus proposes a novel active learning framework for realistic dataset annotation.
Ranked #1 on
Image Classification
on Food-101
(using extra training data)
Measuring the Impact of (Psycho-)Linguistic and Readability Features and Their Spill Over Effects on the Prediction of Eye Movement Patterns
There is a growing interest in the combined use of NLP and machine learning methods to predict gaze patterns during naturalistic reading.
X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation
2) Squeeze Stage: X-Learner condenses the model to a reasonable size and learns the universal and generalizable representation for various tasks transferring.
PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
Methods for 3D lane detection have been recently proposed to address the issue of inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.).
Ranked #5 on
3D Lane Detection
on Apollo Synthetic 3D Lane
MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection
In this paper, we introduce the first DETR framework for Monocular DEtection with a depth-guided TRansformer, named MonoDETR.
3D Object Detection From Monocular Images
Autonomous Driving
+3
POS-BERT: Point Cloud One-Stage BERT Pre-Training
We propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process.
Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition
Learning spatial-temporal relation among multiple actors is crucial for group activity recognition.
Pushing on Personality Detection from Verbal Behavior: A Transformer Meets Text Contours of Psycholinguistic Features
Research at the intersection of personality psychology, computer science, and linguistics has recently focused increasingly on modeling and predicting personality from language use.
Cross Domain Object Detection by Target-Perceived Dual Branch Distillation
It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention.
ConvMAE: Masked Convolution Meets Masked Autoencoders
Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT, leading to state-of-the-art performances on image classification, detection and semantic segmentation.
Activating More Pixels in Image Super-Resolution Transformer
In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement.
Ranked #1 on
Image Super-Resolution
on Set5 - 2x upscaling
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Blueprint Separable Residual Network for Efficient Image Super-Resolution
One is the usage of blueprint separable convolution (BSConv), which takes place of the redundant convolution operation.
Evaluating the Generalization Ability of Super-Resolution Networks
However, research on the generalization ability of Super-Resolution (SR) networks is currently absent.
Vision Transformer Adapter for Dense Predictions
This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT).
Ranked #4 on
Semantic Segmentation
on PASCAL Context
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
By fine-tuning on downstream tasks, Point-M2AE achieves 86. 43% accuracy on ScanObjectNN, +3. 36% to the second-best, and largely benefits the few-shot classification, part segmentation and 3D object detection with the hierarchical pre-training scheme.
Ranked #4 on
3D Point Cloud Linear Classification
on ModelNet40
(using extra training data)
You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction
Challenging illumination conditions (low-light, under-exposure and over-exposure) in the real world not only cast an unpleasant visual appearance but also taint the computer vision tasks.
Ranked #2 on
Image Enhancement
on Exposure-Errors
Siamese Image Modeling for Self-Supervised Vision Representation Learning
Driven by these analysis, we propose Siamese Image Modeling (SiameseIM), which predicts the dense representations of an augmented view, based on another masked view from the same image but with different augmentations.
Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot
Equipped with a wide span of sensors, predominant autonomous driving solutions are becoming more modular-oriented for safe system design.
Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline
The two branches are connected so that the control branch receives corresponding guidance from the trajectory branch at each time step.
Ranked #3 on
Autonomous Driving
on CARLA Leaderboard
CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm
Inspired by prompting approaches from NLP, we creatively reinterpret point cloud generation and refinement as the prompting and predicting stages, respectively.
HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints
The in-memory approximate nearest neighbor search (ANNS) algorithms have achieved great success for fast high-recall query processing, but are extremely inefficient when handling hybrid queries with unstructured (i. e., feature vectors) and structured (i. e., related attributes) constraints.
Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification
On top of that, the performance of Tip-Adapter can be further boosted to be state-of-the-art on ImageNet by fine-tuning the cache model for 10$\times$ fewer epochs than existing methods, which is both effective and efficient.
GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation
Specifically, our current work incorporates three different stages, stylization, destylization, and font transfer, respectively, into a unified platform with a single powerful encoder network and two separate style generator networks, one for font transfer, the other for stylization and destylization.
Vision-Centric BEV Perception: A Survey
In recent years, vision-centric Bird's Eye View (BEV) perception has garnered significant interest from both industry and academia due to its inherent advantages, such as providing an intuitive representation of the world and being conducive to data fusion.
Frozen CLIP Models are Efficient Video Learners
Video recognition has been dominated by the end-to-end learning paradigm -- first initializing a video recognition model with weights of a pretrained image model and then conducting end-to-end training on videos.
Ranked #26 on
Action Classification
on Kinetics-400
(using extra training data)
Recurrent Bilinear Optimization for Binary Neural Networks
To address this issue, Recurrent Bilinear Optimization is proposed to improve the learning process of BNNs (RBONNs) by associating the intrinsic bilinear variables in the back propagation process.
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.
Collaboration of Pre-trained Models Makes Better Few-shot Learner
In this paper, we propose CoMo, a Collaboration of pre-trained Models that incorporates diverse prior knowledge from various pre-training paradigms for better few-shot learning.
Low-Resolution Action Recognition for Tiny Actions Challenge
Second, these activities are naturally distributed in a long-tailed way.
Efficient Image Super-Resolution using Vast-Receptive-Field Attention
In this work, we design an efficient SR network by improving the attention mechanism.
Hierarchical and Progressive Image Matting
In this paper, we propose an end-to-end Hierarchical and Progressive Attention Matting Network (HAttMatting++), which can better predict the opacity of the foreground from single RGB images without additional input.
Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting
This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting.
VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection
For this reason, we propose to advance research areas of video understanding, with a shift from traditional action recognition to industrial anomaly analysis.
PalGAN: Image Colorization with Palette Generative Adversarial Networks
Multimodal ambiguity and color bleeding remain challenging in colorization.
Demystify Transformers & Convolutions in Modern Image Deep Networks
Our experiments on various tasks and an analysis of inductive bias show a significant performance boost due to advanced network-level and block-level designs, but performance differences persist among different STMs.
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state.
Ranked #1 on
Instance Segmentation
on COCO test-dev
(AP50 metric, using extra
training data)
Stare at What You See: Masked Image Modeling without Reconstruction
However, unlike the low-level features such as pixel values, we argue the features extracted by powerful teacher models already encode rich semantic correlation across regions in an intact image. This raises one question: is reconstruction necessary in Masked Image Modeling (MIM) with a teacher model?
Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks
In this paper, we propose Uni-Perceiver v2, which is the first generalist model capable of handling major large-scale vision and vision-language tasks with competitive performance.
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
UniFormer has successfully alleviated this issue, by unifying convolution and self-attention as a relation aggregator in the transformer format.
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
It has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models.
Ranked #2 on
Semantic Segmentation
on ADE20K
(using extra training data)
InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges
In this report, we present our champion solutions to five tracks at Ego4D challenge.
Ranked #1 on
State Change Object Detection
on Ego4D
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
The proposed method is verified with a wide spectrum of traditional and modern image backbones and achieves new SoTA results on the large-scale nuScenes dataset.
Ranked #5 on
3D Object Detection
on Rope3D
ResFormer: Scaling ViTs with Multi-Resolution Training
We introduce, ResFormer, a framework that is built upon the seminal idea of multi-resolution training for improved performance on a wide spectrum of, mostly unseen, testing resolutions.
Improving Training and Inference of Face Recognition Models via Random Temperature Scaling
Intuitively, FR algorithms can benefit from both the estimation of uncertainty and the detection of out-of-distribution (OOD) samples.
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard.
Ranked #1 on
Common Sense Reasoning
on ReCoRD
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary frameworks in a learnable manner to boost various video applications.
Ranked #1 on
Action Recognition
on Something-Something V1
(using extra training data)
Diff-Font: Diffusion Model for Robust One-Shot Font Generation
Specifically, a large stroke-wise dataset is constructed, and a stroke-wise diffusion model is proposed to preserve the structure and the completion of each generated character.
Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders
Pre-training by numerous image data has become de-facto for robust 2D representations.
Ranked #2 on
3D Point Cloud Linear Classification
on ModelNet40
(using extra training data)
3D Point Cloud Linear Classification
Few-Shot 3D Point Cloud Classification
(Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplification
State-of-the-art text simplification (TS) systems adopt end-to-end neural network models to directly generate the simplified version of the input text, and usually function as a blackbox.
MANTIS at TSAR-2022 Shared Task: Improved Unsupervised Lexical Simplification with Pretrained Encoders
In this paper we present our contribution to the TSAR-2022 Shared Task on Lexical Simplification of the EMNLP 2022 Workshop on Text Simplification, Accessibility, and Readability.
