Search Results for author:
Found 511 papers, 249 papers with code
Complex Event Detection via Multi-source Video Attributes
Compared to complex event videos, these external videos contain simple contents such as objects, scenes and actions which are the basic elements of complex events.
Harry Potter's Marauder's Map: Localizing and Tracking Multiple Persons-of-Interest by Nonnegative Discretization
A device just like Harry Potter's Marauder's Map, which pinpoints the location of each person-of-interest at all times, provides invaluable information for analysis of surveillance videos.
Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising
As compared to the conventional RGB or gray-scale images, multispectral images (MSI) can deliver more faithful representation for real scenes, and enhance the performance of many computer vision tasks.
Parsing Occluded People
Occlusion poses a significant difficulty for object recognition due to the combinatorial diversity of possible occlusion patterns.
Event Detection using Multi-Level Relevance Labels and Multiple Features
We address the challenging problem of utilizing related exemplars for complex event detection while multiple features are available.
A Discriminative CNN Video Representation for Event Detection
In this paper, we propose a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available.
A Convex Formulation for Spectral Shrunk Clustering
Thus, applying manifold information obtained from the original space to the clustering process in a low-dimensional subspace is prone to inferior performance.
Semi-supervised Feature Analysis by Mining Correlations among Multiple Tasks
In this paper, we propose a novel semi-supervised feature selection framework by mining correlations among multiple tasks and apply it to different multimedia applications.
Balanced k-Means and Min-Cut Clustering
Clustering is an effective technique in data mining to generate groups that are the matter of interest.
A Convex Sparse PCA for Feature Analysis
In addition, based on the sparse model used in CSPCA, an optimal weight is assigned to each of the original feature, which in turn provides the output with good interpretability.
Improved Spectral Clustering via Embedded Label Propagation
Our algorithm is built upon two advancements of the state of the art:1) label propagation, which propagates a node\'s labels to neighboring nodes according to their proximity; and 2) manifold learning, which has been widely used in its capacity to leverage the manifold structure of data points.
Compound Rank-k Projections for Bilinear Analysis
In many real-world applications, data are represented by matrices or high-order tensors.
Unsupervised Domain Adaptation with Feature Embeddings
Representation learning is the dominant technique for unsupervised domain adaptation, but existing approaches often require the specification of "pivot features" that generalize across domains, which are selected by task-specific heuristics.
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel image captions.
Group $K$-Means
We study how to learn multiple dictionaries from a dataset, and approximate any data point by the sum of the codewords each chosen from the corresponding dictionary.
Depth-based hand pose estimation: methods, data, and challenges
To spur further progress we introduce a challenging new dataset with diverse, cluttered scenes.
Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
In particular, we propose a transposed weight sharing scheme, which not only improves performance on image captioning, but also makes the model more suitable for the novel concept learning task.
DevNet: A Deep Event Network for Multimedia Event Detection and Evidence Recounting
Taking key frames of videos as input, we first detect the event of interest at the video level by aggregating the CNN features of the key frames.
Learning From Massive Noisy Labeled Data for Image Classification
To demonstrate the effectiveness of our approach, we collect a large-scale real-world clothing classification dataset with both noisy and clean labels.
Indexing of CNN Features for Large Scale Image Search
The convolutional neural network (CNN) features can give a good description of image content, which usually represent images with unique global vectors.
Insurance Premium Prediction via Gradient Tree-Boosted Tweedie Compound Poisson Models
The Tweedie GLM is a widely used method for predicting insurance premiums.
Methodology
DenseBox: Unifying Landmark Localization with End to End Object Detection
How can a single fully convolutional neural network (FCN) perform on object detection?
BLASX: A High Performance Level-3 BLAS Library for Heterogeneous Multi-GPU Computing
Basic Linear Algebra Subprograms (BLAS) are a set of low level linear algebra kernels widely adopted by applications involved with the deep learning and scientific computing.
Distributed, Parallel, and Cluster Computing
Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
The sentence generator produces one simple short sentence that describes a specific short video interval.
Attention to Scale: Scale-aware Semantic Image Segmentation
We adapt a state-of-the-art semantic image segmentation model, which we jointly train with multi-scale input images and the attention model.
Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning
In this paper, we propose a new approach, namely Hierarchical Recurrent Neural Encoder (HRNE), to exploit temporal information of videos.
Uncovering Temporal Context for Video Question and Answering
In this work, we introduce Video Question Answering in temporal domain to infer the past, describe the present and predict the future.
Overcoming Language Variation in Sentiment Analysis with Social Attention
Variation in language is ubiquitous, particularly in newer forms of writing such as social media.
Depth-Based Hand Pose Estimation: Data, Methods, and Challenges
To spur further progress we introduce a challenging new dataset with diverse, cluttered scenes.
Look and Think Twice: Capturing Top-Down Visual Attention With Feedback Convolutional Neural Networks
While feedforward deep convolutional neural networks (CNNs) have been a great success in computer vision, it is important to remember that the human visual contex contains generally more feedback connections than foward connections.
Dynamic Concept Composition for Zero-Example Event Detection
In this paper, we focus on automatically detecting events in unconstrained videos without the use of any visual training exemplars.
Part-of-Speech Tagging for Historical English
We evaluate several domain adaptation methods on the task of tagging Early Modern English and Modern British English texts in the Penn Corpora of Historical English.
Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent
Then we present the study of ISGD batch size to the learning rate, parallelism, synchronization cost, system saturation and scalability.
Fully Convolutional Attention Networks for Fine-Grained Recognition
Fine-grained recognition is challenging due to its subtle local inter-class differences versus large intra-class variations such as poses.
Person Re-identification in the Wild
Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification accuracy and assessing the effectiveness of different detectors for re-identification.
CNN-RNN: A Unified Framework for Multi-label Image Classification
While deep convolutional neural networks (CNNs) have shown a great success in single-label image classification, it is important to note that real world images generally contain multiple labels, which could correspond to different objects, scenes, actions and attributes in an image.
Long-Term Identity-Aware Multi-Person Tracking for Surveillance Video Summarization
Therefore, our tracker propagates identity information to frames without recognized faces by uncovering the appearance and spatial manifold formed by person detections.
They Are Not Equally Reliable: Semantic Event Search Using Differentiated Concept Classifiers
Complex event detection on unconstrained Internet videos has seen much progress in recent years.
You Lead, We Exceed: Labor-Free Video Concept Learning by Jointly Exploiting Web Videos and Images
The Web images are then filtered by the learnt network and the selected images are additionally fed into the network to enhance the architecture and further trim the videos.
Strategies for Searching Video Content with Text Queries or Video Examples
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search.
SIFT Meets CNN: A Decade Survey of Instance Retrieval
This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods.
S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking
Non-linear models recently receive a lot of attention as people are starting to discover the power of statistical and embedding features.
Toward Socially-Infused Information Extraction: Embedding Authors, Mentions, and Entities
Entity linking is the task of identifying mentions of entities in text, and linking them to entries in a knowledge base.
Person Re-identification: Past, Present and Future
Person re-identification (re-ID) has become increasingly popular in the community due to its application and research significance.
Ranked #83 on
Person Re-Identification
on DukeMTMC-reID
Optimizing Memory Efficiency for Deep Convolutional Neural Networks on GPUs
Leveraging large data sets, deep Convolutional Neural Networks (CNNs) achieve state-of-the-art recognition accuracy.
A Discriminatively Learned CNN Embedding for Person Re-identification
We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i. e, verification and classification models.
Ranked #1 on
Person Re-Identification
on Market-1501+500k
Bidirectional Multirate Reconstruction for Temporal Modeling in Videos
This learning process makes the learned model more capable of dealing with motion speed variance.
Few-Shot Object Recognition from Machine-Labeled Web Images
Then, we demonstrate that with our model, machine-labeled image annotations are very effective and abundant resources to perform object recognition on novel categories.
Personalized Video Recommendation Using Rich Contents from Videos
In the existing video recommender systems, the models make the recommendations based on the user-video interactions and single specific content features.
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
We verify the proposed method on a practical problem: person re-identification (re-ID).
Ranked #4 on
Person Re-Identification
on CUHK03
Fine-Grained Image Classification
Generative Adversarial Network
+2
Pose Invariant Embedding for Deep Person Re-identification
Second, to reduce the impact of pose estimation errors and information loss during PoseBox construction, we design a PoseBox fusion (PBF) CNN architecture that takes the original image, the PoseBox, and the pose estimation confidence as input.
A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval
Additionally, a trivial solution, \ie, directly using the predicted class label for cross-media retrieval, is tested.
Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval
Second, texts in these datasets are written in well-organized language, leading to inconsistency with realistic applications.
Improving Person Re-identification by Attribute and Identity Learning
Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions.
Ranked #75 on
Person Re-Identification
on DukeMTMC-reID
An End-to-End Approach to Natural Language Object Retrieval via Context-Aware Deep Reinforcement Learning
We propose an end-to-end approach to the natural language object retrieval task, which localizes an object within an image according to a natural language description, i. e., referring expression.
More is Less: A More Complicated Network with Less Inference Complexity
In this paper, we present a novel and general network structure towards accelerating the inference process of convolutional neural networks, which is more complicated in network structure yet with less inference complexity.
Dynamic Computational Time for Visual Attention
We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM).
GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
In this work, we propose a model that can learn object transfiguration from two unpaired sets of images: one set containing images that "have" that kind of object, and the other set being the opposite, with the mild constraint that the objects be located approximately at the same place.
Unsupervised Learning Layers for Video Analysis
This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones.
Unsupervised Person Re-identification: Clustering and Fine-tuning
Progressively, pedestrian clustering and the CNN model are improved simultaneously until algorithm convergence.
Ranked #12 on
Unsupervised Person Re-Identification
on DukeMTMC-reID
Few-Example Object Detection with Model Communication
Experiments on PASCAL VOC'07, MS COCO'14, and ILSVRC'13 indicate that by using as few as three or four samples selected for each category, our method produces very competitive results when compared to the state-of-the-art weakly-supervised approaches using a large number of image-level labels.
Ranked #1 on
Weakly Supervised Object Detection
on MS COCO
Pedestrian Alignment Network for Large-scale Person Re-identification
This task aims to search a query person in a large image pool.
Ranked #1 on
Person Re-Identification
on CUHK03 (detected)
UTS submission to Google YouTube-8M Challenge 2017
In this paper, we present our solution to Google YouTube-8M Video Classification Challenge 2017.
PatchShuffle Regularization
This paper focuses on regularizing the training of the convolutional neural network (CNN).
Robust PCA by Manifold Optimization
Robust PCA is a widely used statistical procedure to recover a underlying low-rank matrix with grossly corrupted observations.
Random Erasing Data Augmentation
In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).
Ranked #4 on
Image Classification
on Fashion-MNIST
An Improved Residual LSTM Architecture for Acoustic Modeling
Long Short-Term Memory (LSTM) is the primary recurrent neural networks architecture for acoustic modeling in automatic speech recognition systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks
For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer.
Ranked #12 on
Image Classification
on SVHN
Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition
The designed ReST has an intrinsic recursive structure and is capable of progressively aligning faces to a canonical one, even those with large variations.
Learning Discriminative Latent Attributes for Zero-Shot Classification
Zero-shot learning (ZSL) aims to transfer knowledge from observed classes to the unseen classes, based on the assumption that both the seen and unseen classes share a common semantic space, among which attributes enjoy a great popularity.
Complex Event Detection by Identifying Reliable Shots From Untrimmed Videos
relevant) to the given event class, we formulate this task as a multi-instance learning (MIL) problem by taking each video as a bag and the video shots in each video as instances.
Nanophotonic Particle Simulation and Inverse Design Using Artificial Neural Networks
We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles.
Computational Physics Applied Physics Optics
Dual-Path Convolutional Image-Text Embeddings with Instance Loss
In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space.
Ranked #1 on
Cross-Modal Retrieval
on CUHK-PEDES
Occlusion Aware Unsupervised Learning of Optical Flow
Especially on KITTI dataset where abundant unlabeled samples exist, our unsupervised method outperforms its counterpart trained with supervised learning.
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
To this end, we propose to preserve two types of unsupervised similarities, 1) self-similarity of an image before and after translation, and 2) domain-dissimilarity of a translated source image and a target image.
Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
RPP re-assigns these outliers to the parts they are closest to, resulting in refined parts with enhanced within-part consistency.
Ranked #3 on
Person Re-Identification
on UAV-Human
Camera Style Adaptation for Person Re-identification
In this paper, we explicitly consider this challenge by introducing camera style (CamStyle) adaptation.
Ranked #71 on
Person Re-Identification
on DukeMTMC-reID
Alibaba at IJCNLP-2017 Task 1: Embedding Grammatical Features into LSTMs for Chinese Grammatical Error Diagnosis Task
This paper introduces Alibaba NLP team system on IJCNLP 2017 shared task No.
Ranked #1 on
2D Human Pose Estimation
on Alibaba Cluster Trace
(using extra training data)
Prognostication of chronic disorders of consciousness using brain functional networks and clinical characteristics
Disorders of consciousness are a heterogeneous mixture of different diseases or injuries.
Neurons and Cognition
Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification
This paper considers the task of thorax disease classification on chest X-ray images.
Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
Second, we estimate the posterior label distribution of the unlabeled data for target network training.
Collective Entity Disambiguation with Structured Gradient Tree Boosting
To the best of our knowledge, our work is the first one that employs the structured gradient tree boosting (SGTB) algorithm for collective entity disambiguation.
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)
Decoupled Novel Object Captioner
Thus, the sequence model can be decoupled from the novel object descriptions.
Adversarial Complementary Learning for Weakly Supervised Object Localization
With such an adversarial learning, the two parallel-classifiers are forced to leverage complementary object regions for classification and can finally generate integral object localization together.
Ranked #2 on
Weakly-Supervised Object Localization
on ILSVRC 2016
Deploy Large-Scale Deep Neural Networks in Resource Constrained IoT Devices with Local Quantization Region
Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time.
Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class.
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).
Improve Neural Entity Recognition via Multi-Task Data Selection and Constrained Decoding
Entity recognition is a widely benchmarked task in natural language processing due to its massive applications.
3D Pose Estimation for Fine-Grained Object Categories
The new dataset is available at www. umiacs. umd. edu/~wym/3dpose. html
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
In this paper, we present supervision-by-registration, an unsupervised approach to improve the precision of facial landmark detectors on both images and video.
Ranked #1 on
Facial Landmark Detection
on 300-VW (C)
Macro-Micro Adversarial Network for Human Parsing
To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN).
Ranked #12 on
Semantic Segmentation
on LIP val
Self-produced Guidance for Weakly-supervised Object Localization
A stagewise approach is proposed to incorporate high confident object regions to learn the SPG masks.
Ranked #1 on
Weakly-Supervised Object Localization
on ILSVRC 2015
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
Therefore, the network trained by our method has a larger model capacity to learn from the training data.
Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks
With asymptotic pruning, the information of the training set would be gradually concentrated in the remaining filters, so the subsequent training and pruning process would be stable.
Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions
We validate the effectiveness of our ASST on two large-scale datasets.
Convolutional Neural Networks with Recurrent Neural Filters
We introduce a class of convolutional neural networks (CNNs) that utilize recurrent neural networks (RNNs) as convolution filters.
Ranked #11 on
Sentiment Analysis
on SST-5 Fine-grained classification
A Unified Analysis of Stochastic Momentum Methods for Deep Learning
However, their theoretical analysis of convergence of the training objective and the generalization error for prediction is still under-explored.
RCAA: Relational Context-Aware Agents for Person Search
In this paper, we address this problem by training relational context-aware agents which learn the actions to localize the target person from the gallery of whole scene images.
Compound Memory Networks for Few-shot Video Classification
In this paper, we propose a new memory network structure for few-shot video classification by making the following contributions.
Generalizing A Person Retrieval Model Hetero- and Homogeneously
Person re-identification (re-ID) poses unique challenges for unsupervised domain adaptation (UDA) in that classes in the source and target sets (domains) are entirely different and that image variations are largely caused by cameras.
Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space.
DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments
It is one of the state-of-the-art SLAM systems in high-dynamic environments.
Robotics
Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
We consider the problem of unsupervised domain adaptation in semantic segmentation.
Ranked #8 on
Semantic Segmentation
on DADA-seg
Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
To capitalize on the information from unlabeled nodes to boost the training for GCN, we propose a novel framework named Self-Ensembling GCN (SEGCN), which marries GCN with Mean Teacher - another powerful model in semi-supervised learning.
Ranked #4 on
Node Classification
on Cora: fixed 20 node per class
Learning Discriminators as Energy Networks in Adversarial Learning
In this work, we propose to refine the predictions of structured prediction models by effectively integrating discriminative models into the prediction.
Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos
Then the whole scene is decomposed into moving foreground and static background by compar- ing the estimated optical flow and rigid flow derived from the depth and ego-motion.
Improving Annotation for 3D Pose Dataset of Fine-Grained Object Categories
Existing 3D pose datasets of object categories are limited to generic object types and lack of fine-grained information.
SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
In this way, the possibilities embedded in the produced similarity maps can be adapted to guide the process of segmenting objects.
Ranked #89 on
Few-Shot Semantic Segmentation
on PASCAL-5i (5-Shot)
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration
In this paper, we analyze this norm-based criterion and point out that its effectiveness depends on two requirements that are not always met: (1) the norm deviation of the filters should be large; (2) the minimum norm of the filters should be small.
Zero-Shot Transfer VQA Dataset
Therefore, toaccelerate this research, we propose a newzero-shot transfer VQA(ZST-VQA)dataset by reorganizing the existing VQA v1. 0 dataset in the way that duringtraining, some words appear only in one module (i. e. questions) but not in theother (i. e. answers).
Deep Unfolded Robust PCA with Application to Clutter Suppression in Ultrasound
We compare the performance of the suggested deep network on both simulations and in-vivo rat brain scans, with a commonly practiced deep-network architecture and the fast iterative shrinkage algorithm, and show that our architecture exhibits better image quality and contrast.
Similarity-preserving Image-image Domain Adaptation for Person Re-identification
It first preserves two types of unsupervised similarity, namely, self-similarity of an image before and after translation, and domain-dissimilarity of a translated source image and a target image.
Contrastive Adaptation Network for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain.
Ranked #7 on
Domain Adaptation
on Office-31
Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
We propose to automatically search for a CNN architecture that is specifically suitable for the reID task.
Ranked #9 on
Person Re-Identification
on CUHK03 detected
Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation
For unsupervised domain adaptation problems, the strategy of aligning the two domains in latent feature space through adversarial learning has achieved much progress in image classification, but usually fails in semantic segmentation tasks in which the latent representations are overcomplex.
Operation-aware Neural Networks for User Response Prediction
Many deep models are proposed to automatically learn high-order feature interactions.
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
If the initial image is not well initialized, the following processes can hardly refine the image to a satisfactory quality.
Ranked #6 on
Text-to-Image Generation
on CUB
(Inception score metric)
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
To achieve this goal, an exemplar memory is introduced to store features of the target domain and accommodate the three invariance properties.
Domain Adaptive Person Re-Identification
Person Re-Identification
+1
Filter Pruning by Switching to Neighboring CNNs with Good Attributes
In addition, when evaluating the filter importance, only the magnitude information of the filters is considered.
Revisiting EmbodiedQA: A Simple Baseline and Beyond
In this paper, we empirically study this problem and introduce 1) a simple yet effective baseline that achieves promising performance; 2) an easier and practical setting for EmbodiedQA where an agent has a chance to adapt the trained model to a new environment before it actually answers users questions.
Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation
Specifically, our method employs an adversarial feature adaptation model for visual representation transfer and a policy mimic strategy for policy behavior imitation.
Joint Discriminative and Generative Learning for Person Re-identification
To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end.
Ranked #1 on
Person Re-Identification
on UAV-Human
Image-to-Image Translation
Unsupervised Domain Adaptation
+1
Cubic LSTMs for Video Prediction
Predicting future frames in videos has become a promising direction of research for both computer vision and robot learning communities.
Network Pruning via Transformable Architecture Search
The maximum probability for the size in each distribution serves as the width and depth of the pruned network, whose parameters are learned by knowledge transfer, e. g., knowledge distillation, from the original networks.
Ranked #1 on
Network Pruning
on CIFAR-10
Syntax-Infused Variational Autoencoder for Text Generation
We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences.
Query-efficient Meta Attack to Deep Neural Networks
Black-box attack methods aim to infer suitable attack patterns to targeted DNN models by only using output feedback of the models and the corresponding input queries.
FASTER Recurrent Networks for Efficient Video Classification
FASTER aims to leverage the redundancy between neighboring clips and reduce the computational cost by learning to aggregate the predictions from models of different complexities.
Ranked #26 on
Action Recognition
on UCF101
Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019
In this report, we present the Baidu-UTS submission to the EPIC-Kitchens Action Recognition Challenge in CVPR 2019.
A Semi-Markov Structured Support Vector Machine Model for High-Precision Named Entity Recognition
Named entity recognition (NER) is the backbone of many NLP solutions.
What You Say and How You Say It Matters: Predicting Stock Volatility Using Verbal and Vocal Cues
Prior research has shown that textual information in a firm{'}s financial statement can be used to predict its stock{'}s risk level.
Adaptive Exploration for Unsupervised Person Re-Identification
However, a problem of the adaptive selection is that, when an image has too many neighborhoods, it is more likely to attract other images as its neighborhoods.
Learning to Adapt Invariance in Memory for Person Re-identification
This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain.
Ranked #7 on
Unsupervised Domain Adaptation
on Market to MSMT
Cascaded Revision Network for Novel Object Captioning
By this novel cascaded captioning-revising mechanism, CRN can accurately describe images with unseen objects.
Attract or Distract: Exploit the Margin of Open Set
In this paper, we exploit the semantic structure of open set data from two aspects: 1) Semantic Categorical Alignment, which aims to achieve good separability of target known classes by categorically aligning the centroid of target with the source.
An Algorithm for Graph-Fused Lasso Based on Graph Decomposition
In comparison, this work proposes to decompose the objective function into two components, where one component is the loss function plus part of the total variation penalty, and the other component is the remaining total variation penalty.
Optimization and Control Computation
Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection
A typical approach is to (1) train a detector on the labeled images; (2) generate new training samples using this detector's prediction as pseudo labels of unlabeled images; (3) retrain the detector on the labeled samples and partial pseudo labeled samples.
Ranked #1 on
Facial Landmark Detection
on 300W (Full)
(using extra training data)
Recognizing Part Attributes with Insufficient Data
Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications.
Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning
We propose a novel adaptive transfer learning framework, learning to transfer learn (L2TL), to improve performance on a target dataset by careful extraction of the related information from a source dataset.
Dialog Intent Induction with Deep Multi-View Clustering
We introduce the dialog intent induction task and present a novel deep multi-view clustering approach to tackle the problem.
LSMI-Sinkhorn: Semi-supervised Mutual Information Estimation with Optimal Transport
To estimate the mutual information from data, a common practice is preparing a set of paired samples $\{(\mathbf{x}_i,\mathbf{y}_i)\}_{i=1}^n \stackrel{\mathrm{i. i. d.
Multi-scale discriminative Region Discovery for Weakly-Supervised Object Localization
On ILSVRC 2016, the proposed method yields the Top-1 localization error of 48. 65\%, which outperforms previous results by 2. 75\%.
Gated Channel Transformation for Visual Recognition
This lightweight layer incorporates a simple l2 normalization, enabling our transformation unit applicable to operator-level without much increase of additional parameters.
Searching for A Robust Neural Architecture in Four GPU Hours
To avoid traversing all the possibilities of the sub-graphs, we develop a differentiable sampler over the DAG.
Ranked #18 on
Neural Architecture Search
on CIFAR-10
One-Shot Neural Architecture Search via Self-Evaluated Template Network
In this paper, we propose a Self-Evaluated Template Network (SETN) to improve the quality of the architecture candidates for evaluation so that it is more likely to cover competitive candidates.
Ranked #18 on
Neural Architecture Search
on NAS-Bench-201, ImageNet-16-120
(Accuracy (Val) metric)
PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing
We apply PointRNN, PointGRU and PointLSTM to moving point cloud prediction, which aims to predict the future trajectories of points in a set given their history movements.
Self-Correction for Human Parsing
To tackle the problem of learning with label noises, this work introduces a purification strategy, called Self-Correction for Human Parsing (SCHP), to progressively promote the reliability of the supervised labels as well as the learned models.
Ranked #2 on
Human Part Segmentation
on PASCAL-Part
Instance-Invariant Domain Adaptive Object Detection via Progressive Disentanglement
Most state-of-the-art methods of object detection suffer from poor generalization ability when the training and test data are from different domains, e. g., with different styles.
Connective Cognition Network for Directional Visual Commonsense Reasoning
Inspired by this idea, towards VCR, we propose a connective cognition network (CCN) to dynamically reorganize the visual neuron connectivity that is contextualized by the meaning of questions and answers.
DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking
However, in practice it is rather common to have no un-paired images in real deraining task, in such cases how to remove the rain streaks in an unsupervised way will be a very challenging task due to lack of constraints between images and hence suffering from low-quality recovery results.
Unsupervised Scene Adaptation with Memory Regularization in vivo
We consider the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data.
Ranked #1 on
Domain Adaptation
on SYNTHIA-to-Cityscapes Labels
Utterance-level Permutation Invariant Training with Latency-controlled BLSTM for Single-channel Multi-talker Speech Separation
The experimental results show that uPIT outperforms cPIT when LC-BLSTM is used during inference.
Very Long Natural Scenery Image Prediction by Outpainting
The second challenge is how to maintain high quality in generated results, especially for multi-step generations in which generated regions are spatially far away from the initial input.
NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
A variety of algorithms search architectures under different search space.
Progressive Local Filter Pruning for Image Retrieval Acceleration
To verify this, we evaluate our method on two widely-used image retrieval datasets, i. e., Oxford5k and Paris6K, and one person re-identification dataset, i. e., Market-1501.
Lane Detection in Low-light Conditions Using an Efficient Data Enhancement : Light Conditions Style Transfer
Nowadays, deep learning techniques are widely used for lane detection, but application in low-light conditions remains a challenge until this day.
Symbiotic Attention with Privileged Information for Egocentric Action Recognition
Due to the large action vocabulary in egocentric video datasets, recent studies usually utilize a two-branch structure for action recognition, ie, one branch for verb classification and the other branch for noun classification.
Ranked #4 on
Egocentric Activity Recognition
on EGTEA
Dynamic Inference: A New Approach Toward Efficient Video Action Recognition
In a nutshell, we treat input frames and network depth of the computational graph as a 2-dimensional grid, and several checkpoints are placed on this grid in advance with a prediction module.
University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization
To our knowledge, University-1652 is the first drone-based geo-localization dataset and enables two new tasks, i. e., drone-view target localization and drone navigation.
Ranked #6 on
Drone navigation
on University-1652
Grounded and Controllable Image Completion by Incorporating Lexical Semantics
Existing image completion procedure is highly subjective by considering only visual context, which may trigger unpredictable results which are plausible but not faithful to a grounded knowledge.
Angle-Based Cost-Sensitive Multicategory Classification
To show the usefulness of the framework, two cost-sensitive multicategory boosting algorithms are derived as concrete instances.
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation.
SF-Net: Single-Frame Supervision for Temporal Action Localization
To obtain the single-frame supervision, the annotators are asked to identify only a single frame within the temporal window of an action.
Ranked #5 on
Weakly Supervised Action Localization
on BEOID
Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
Most of previous work on adversarial attack mainly focus on image models, while the vulnerability of video models is less explored.
Collaborative Video Object Segmentation by Foreground-Background Integration
This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation.
Ranked #8 on
Video Object Segmentation
on YouTube-VOS 2019
Memory Aggregation Networks for Efficient Interactive Video Object Segmentation
Interactive video object segmentation (iVOS) aims at efficiently harvesting high-quality segmentation masks of the target object in a video with user interactions.
Ranked #5 on
Interactive Video Object Segmentation
on DAVIS 2017
(AUC-J metric)
Context Modulated Dynamic Networks for Actor and Action Video Segmentation with Language Queries
Actor and action video segmentation with language queries aims to segment out the expression referred objects in the video.
Ranked #10 on
Referring Expression Segmentation
on J-HMDB
One Model to Recognize Them All: Marginal Distillation from NER Models with Different Tag Sets
Named entity recognition (NER) is a fundamental component in the modern language understanding pipeline.
OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World
In this paper, we tackle the problem of discovering new classes in unlabeled visual data given labeled data from disjoint classes.
Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation
We aim at the problem named One-Shot Unsupervised Domain Adaptation.
domain classification
One-shot Unsupervised Domain Adaptation
+2
VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
This stage relaxes the full alignment between the training and testing domains, as it is agnostic to the target vehicle domain.
Ranked #1 on
Vehicle Re-Identification
on VehicleID
Omni-supervised Facial Expression Recognition via Distilled Data
However, the performance of the current state-of-the-art facial expression recognition (FER) approaches is directly related to the labeled data for training.
Facial Expression Recognition
Facial Expression Recognition (FER)
Feature Robust Optimal Transport for High-dimensional Data
To show the effectiveness of FROT, we propose using the FROT algorithm for the layer selection problem in deep neural networks for semantic correspondence.
Parameter-Efficient Person Re-identification in the 3D Space
To our knowledge, we are among the first attempts to conduct person re-identification in the 3D space.
Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps
To fulfill the direct evaluation, we annotate pixel-level object masks on the ILSVRC validation set.
FinBERT: A Pretrained Language Model for Financial Communications
Contextual pretrained language models, such as BERT (Devlin et al., 2019), have made significant breakthrough in various NLP tasks by training on large scale of unlabeled text re-sources. Financial sector also accumulates large amount of financial communication text. However, there is no pretrained finance specific language models available.
Sketch-Guided Scenery Image Outpainting
In this work, we take the image outpainting one step forward by allowing users to harvest personal custom outpainting results using sketches as the guidance.
Interpretable Operational Risk Classification with Semi-Supervised Variational Autoencoder
To tackle these challenges, we present a semi-supervised text classification framework that integrates multi-head attention mechanism with Semi-supervised variational inference for Operational Risk Classification (SemiORC).
Interpreting Twitter User Geolocation
Identifying user geolocation in online social networks is an essential task in many location-based applications.
Single Image Brightening via Multi-Scale Exposure Fusion with Hybrid Learning
In this paper, a single image brightening algorithm is introduced to brighten such an image.
A Survey on Concept Factorization: From Shallow to Deep Representation Learning
In this paper, we therefore survey the recent advances on CF methodologies and the potential benchmarks by categorizing and summarizing the current methods.
Inter-Image Communication for Weakly Supervised Localization
We learn a feature center for each category and realize the global feature consistency by forcing the object features to approach class-specific centers.
Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents
With the arising concerns for the AI systems provided with direct access to abundant sensitive information, researchers seek to develop more reliable AI with implicit information sources.
DONet: Dual Objective Networks for Skin Lesion Segmentation
Skin lesion segmentation is a crucial step in the computer-aided diagnosis of dermoscopic images.
Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory
With slight modifications, MBJ is applicable for two fundamental visual recognition tasks, \emph{i. e.}, deep image classification and deep metric learning (on long-tailed data).
Ranked #44 on
Long-tail Learning
on CIFAR-100-LT (ρ=100)
Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition
In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition.
Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization
Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas.
Ranked #3 on
Drone navigation
on University-1652
Hierarchical memory decoder for visual narrating
In this article, we devise a novel memory decoder for visual narrating.
Ranked #13 on
Visual Storytelling
on VIST
Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly.
DOTS: Decoupling Operation and Topology in Differentiable Architecture Search
DARTS mainly focuses on the operation search and derives the cell topology from the operation weights.
