Search Results for author:
Found 61 papers, 12 papers with code
Towards Part-aware Monocular 3D Human Pose Estimation: An Architecture Search Approach
With roughly the same computational complexity as previous models, our approach achieves state-of-the-art results on both the single-person and multi-person 3D pose estimation benchmarks.
Prediction and Recovery for Adaptive Low-Resolution Person Re-Identification
In this paper, we propose a novel Prediction, Recovery and Identification (PRI) model for LR re-id, which adaptively recovers missing details by predicting a preferable scale factor based on the image content.
1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)
Our model consists of three modules: the candidate waypoints predictor (CWP), the history enhanced planner and the tryout controller.
Intra Encoding Complexity Control with a Time-Cost Model for Versatile Video Coding
Inspired by rate control algorithms, we propose a scheme to precisely control the intra encoding complexity of VVC.
A Closer Look at Personalization in Federated Image Classification
This paper shows that it is possible to achieve flexible personalization after the convergence of the global model by introducing representation learning.
Generative Compression for Face Video: A Hybrid Scheme
As the latest video coding standard, versatile video coding (VVC) has shown its ability in retaining pixel quality.
Learning the Degradation Distribution for Blind Image Super-Resolution
Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones.
Generalizable Person Re-Identification via Self-Supervised Batch Norm Test-Time Adaption
In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain.
Uncovering the Source of Machine Bias
We find two types of biases in gender, preference-based bias and belief-based bias, are present in human evaluators' decisions.
Landmark-RxR: Solving Vision-and-Language Navigation with Fine-Grained Alignment Supervision
In Vision-and-Language Navigation (VLN) task, an agent is asked to navigate inside 3D indoor environments following given instructions.
SIN:Superpixel Interpolation Network
The former is non-differentiable and the latter needs a non-differentiable post-processing step to enforce connectivity, which constraints the integration of superpixels and downstream tasks.
Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing
However, it is noted that ASM-based SIDM degrades its performance in dehazing real world hazy images due to the limited modelling ability of ASM where the atmospheric light factor (ALF) and the angular scattering coefficient (ASC) are assumed as constants for one image.
Adaptive Dilated Convolution For Human Pose Estimation
It can generate and fuse multi-scale features of the same spatial sizes by setting different dilation rates for different channels.
Neighbor-view Enhanced Model for Vision and Language Navigation
Specifically, our NvEM utilizes a subject module and a reference module to collect contexts from neighbor views.
Hate Speech Detection in Clubhouse
This makes the hate speech detection challenging in new social media like Clubhouse.
Statistical Analysis of Perspective Scores on Hate Speech Detection
It has proven that, state-of-the-art hate speech classifiers are efficient only when tested on the data with the same feature distribution as training data.
CMF: Cascaded Multi-model Fusion for Referring Image Segmentation
To solve this problem, we propose a simple yet effective Cascaded Multi-modal Fusion (CMF) module, which stacks multiple atrous convolutional layers in parallel and further introduces a cascaded branch to fuse visual and linguistic features.
End-to-end Alternating Optimization for Blind Super Resolution
More importantly, \textit{Restorer} is trained with the kernel estimated by \textit{Estimator}, instead of the ground-truth kernel, thus \textit{Restorer} could be more tolerant to the estimation error of \textit{Estimator}.
FDAN: Flow-guided Deformable Alignment Network for Video Super-Resolution
Recently, deformable alignment has drawn extensive attention in VSR community for its remarkable performance, which can adaptively align neighboring frames with the reference one.
FWB-Net:Front White Balance Network for Color Shift Correction in Single Image Dehazing via Atmospheric Light Estimation
However, for images taken in real-world, the illumination is not uniformly distributed over whole image which brings model mismatch and possibly results in color shift of the deep models using ASM.
Clothing Status Awareness for Long-Term Person Re-Identification
This work argues that these approaches in fact are not aware of clothing status (i. e., change or no-change) of a pedestrian.
Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation
However, for bottom-up methods, which need to handle a large variance of human scales and labeling ambiguities, the current practice seems unreasonable.
Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this information by improving the fusion method.
Observation of Magnetic Droplets in Magnetic Tunnel Junctions
Magnetic droplets, a class of highly non-linear magnetodynamical solitons, can be nucleated and stabilized in nanocontact spin-torque nano-oscillators where they greatly increase the microwave output power.
Applied Physics
Pointing to Select: A Fast Pointer-LSTM for Long Text Classification
Recurrent neural networks (RNNs) suffer from well-known limitations and complications which include slow inference and vanishing gradients when processing long sequences in text classification.
Collaborative City Digital Twin For Covid-19 Pandemic: A Federated Learning Solution
In this work, we propose a collaborative city digital twin based on FL, a novel paradigm that allowing multiple city DT to share the local strategy and status in a timely manner.
Actor and Action Modular Network for Text-based Video Segmentation
We first learn the actor-/action-related content for the video and textual query, and then match them in a symmetrical manner to localize the target region.
Ranked #6 on
Referring Expression Segmentation
on J-HMDB
Unfolding the Alternating Optimization for Blind Super Resolution
More importantly, \textit{Restorer} is trained with the kernel estimated by \textit{Estimator}, instead of ground-truth kernel, thus \textit{Restorer} could be more tolerant to the estimation error of \textit{Estimator}.
Ranked #2 on
Blind Super-Resolution
on Set5 - 2x upscaling
Algorithmic Transparency with Strategic Users
We show that, in some cases, even the predictive power of machine learning algorithms may increase if the firm makes them transparent.
Recurrent Deconvolutional Generative Adversarial Networks with Application to Text Guided Video Generation
The RDN is a deconvolutional version of conventional recurrent neural network, which can well model the long-range temporal dependency of generated video frames and make good use of conditional information.
Crowd, Lending, Machine, and Bias
We then use the machine to make investment decisions, and find that the machine benefits not only the lenders but also the borrowers.
Cyclic Differentiable Architecture Search
First, the search network generates an initial architecture for evaluation, and the weights of the evaluation network are optimized.
L-Vector: Neural Label Embedding for Domain Adaptation
We propose a novel neural label embedding (NLE) scheme for the domain adaptation of a deep neural network (DNN) acoustic model with unpaired data samples from source and target domains.
Learning Goal-oriented Dialogue Policy with Opposite Agent Awareness
Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment.
Large-scale Real-time Personalized Similar Product Recommendations
Similar product recommendation is one of the most common scenes in e-commerce.
Advances in Online Audio-Visual Meeting Transcription
This increases marginally to 1. 6% when 50% of the attendees are unknown to the system.
ACMM: Aligned Cross-Modal Memory for Few-Shot Image and Sentence Matching
Image and sentence matching has drawn much attention recently, but due to the lack of sufficient pairwise data for training, most previous methods still cannot well associate those challenging pairs of images and sentences containing rarely appeared regions and words, i. e., few-shot content.
SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification
We observe that if backgrounds in the training and testing datasets are very different, it dramatically introduces difficulties to extract robust pedestrian features, and thus compromises the cross-domain person re-ID performance.
Learning Compact Target-Oriented Feature Representations for Visual Tracking
Many state-of-the-art trackers usually resort to the pretrained convolutional neural network (CNN) model for correlation filtering, in which deep features could usually be redundant, noisy and less discriminative for some certain instances, and the tracking performance might thus be affected.
Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments
Firstly, the global-global alignment in the Global Contrast (GC) module is for matching the global contexts of images and descriptions.
Ranked #10 on
Text based Person Retrieval
on CUHK-PEDES
Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation
To address this problem, it is a good choice to learn to segment with weak supervision from bounding boxes.
RetGK: Graph Kernels based on Return Probabilities of Random Walks
Graph-structured data arise in wide applications, such as computer vision, bioinformatics, and social networks.
Cross-Modal Ranking with Soft Consistency and Noisy Labels for Robust RGB-T Tracking
To address this problem, this paper presents a novel approach to suppress background effects for RGB-T tracking.
DeepMove: Learning Place Representations through Large Scale Movement Data
DeepMove is spatial and temporal context aware.
Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation
Domain shift, which occurs when there is a mismatch between the distributions of training (source) and testing (target) datasets, usually results in poor performance of the trained model on the target domain.
Mask-Guided Contrastive Attention Model for Person Re-Identification
We may be the first one to successfully introduce the binary mask into person ReID task and the first one to propose region-level contrastive learning.
M3: Multimodal Memory Modelling for Video Captioning
Inspired by the facts that memory modelling poses potential advantages to long-term sequential problems [35] and working memory is the key factor of visual attention [33], we propose a Multimodal Memory Model (M3) to describe videos, which builds a visual and textual shared memory to model the long-term visual-textual dependency and further guide visual attention on described visual targets to solve visual-textual alignments.
Relational Network for Skeleton-Based Action Recognition
We introduce the Recurrent Relational Network to learn the spatial features in a single skeleton, followed by a multi-layer LSTM to learn the temporal features in the skeleton sequences.
Ranked #68 on
Skeleton Based Action Recognition
on NTU RGB+D
Multi-pseudo Regularized Label for Generated Data in Person Re-Identification
Unlike the traditional label which usually is a single integral number, the virtual label proposed in this work is a set of weight-based values each individual of which is a number in (0, 1] called multi-pseudo label and reflects the degree of relation between each generated data to every pre-defined class of real data.
Learning Semantic Concepts and Order for Image and Sentence Matching
This mainly arises from that the representation of pixel-level image usually lacks of high-level semantic information as in its matched sentence.
Ranked #10 on
Image Retrieval
on Flickr30K 1K test
A Hierarchical Contextual Attention-based GRU Network for Sequential Recommendation
We fuse the current hidden state and a contextual hidden state built by the attention mechanism, which leads to a more suitable user's overall interest.
See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification
Accordingly, a demanding need is to recognize a person under different cameras, which is called person re-identification.
Instance-aware Image and Sentence Matching with Selective Multimodal LSTM
Based on the observation that such a global similarity arises from a complex aggregation of multiple local similarities between pairwise instances of image (objects) and sentence (words), we propose a selective multimodal Long Short-Term Memory network (sm-LSTM) for instance-aware image and sentence matching.
Ranked #13 on
Image Retrieval
on Flickr30K 1K test
Multimodal Memory Modelling for Video Captioning
In this paper, we propose a Multimodal Memory Model (M3) to describe videos, which builds a visual and textual shared memory to model the long-term visual-textual dependency and further guide global visual attention on described targets.
Sparse Coding for Classification via Discrimination Ensemble
Discriminative sparse coding has emerged as a promising technique in image analysis and recognition, which couples the process of classifier training and the process of dictionary learning for improving the discriminability of sparse codes.
Anchoring and Agreement in Syntactic Annotations
Our agreement results control for parser bias, and are consequential in that they are on par with state of the art parsing performance for English newswire.
Conditional High-Order Boltzmann Machine: A Supervised Learning Model for Relation Learning
Relation learning is a fundamental operation in many computer vision tasks.
Dynamic Texture Recognition via Orthogonal Tensor Dictionary Learning
In addition, based on the proposed dictionary learning method, a DT descriptor is developed, which has better adaptivity, discriminability and scalability than the existing approaches.
Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution
Super resolving a low-resolution video is usually handled by either single-image super-resolution (SR) or multi-frame SR. Single-Image SR deals with each video frame independently, and ignores intrinsic temporal dependency of video frames which actually plays a very important role in video super-resolution.
Ranked #15 on
Video Super-Resolution
on Vid4 - 4x upscaling
T-Drive: Driving Directions Based on Taxi Trajectories
GPS-equipped taxis can be regarded as mobile sensors probing traffic flows on road surfaces, and taxi drivers are usually experienced in finding the fastest (quickest) route to a destination based on their knowledge.
