Search Results for author:
Found 52 papers, 16 papers with code
Box-Level Active Detection
Active learning selects informative samples for annotation within budget, which has proven efficient recently on object detection.
Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning
Based on this observation, we propose a new learning strategy named False Negative Aware Contrastive (FNAC) to mitigate the problem of misleading the training with such false negative samples.
PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection
Masked Autoencoders learn strong visual representations and achieve state-of-the-art results in several independent modalities, yet very few works have addressed their capabilities in multi-modality settings.
Tag2Text: Guiding Vision-Language Model via Image Tagging
This paper presents Tag2Text, a vision language pre-training (VLP) framework, which introduces image tagging into vision-language models to guide the learning of visual-linguistic features.
A Survey of Face Recognition
Recent years witnessed the breakthrough of face recognition with deep convolutional neural networks.
BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks
In order to find them, we further propose a LiDAR-guided sampling strategy to leverage the statistical distribution of LiDAR to determine the heights of local slices.
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object Detection
In this paper, we propose a unified framework named BEV-LGKD to transfer the knowledge in the teacher-student manner.
Multi-latent Space Alignments for Unsupervised Domain Adaptation in Multi-view 3D Object Detection
Vision-Centric Bird-Eye-View (BEV) perception has shown promising potential and attracted increasing attention in autonomous driving.
A Real-Time Fusion Framework for Long-term Visual Localization
In this paper, we present an efficient client-server visual localization architecture that fuses global and local pose estimations to realize promising precision and efficiency.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Efficient Meta-Tuning for Content-aware Neural Video Delivery
Our method significantly reduces the computational cost and achieves even better performance, paving the way for applying neural video delivery techniques to practical applications.
CrossHuman: Learning Cross-Guidance from Multi-Frame Images for Human Reconstruction
We propose CrossHuman, a novel method that learns cross-guidance from parametric human model and multi-frame RGB images to achieve high-quality 3D human reconstruction.
IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training
However, the image-text pairs co-occurrent on the Internet typically lack explicit alignment information, which is suboptimal for VLP.
Mixed Sample Augmentation for Online Distillation
Mixed Sample Regularization (MSR), such as MixUp or CutMix, is a powerful data augmentation strategy to generalize convolutional neural networks.
BANet: Motion Forecasting with Boundary Aware Network
We propose a motion forecasting model called BANet, which means Boundary-Aware Network, and it is a variant of LaneGCN.
Situational Perception Guided Image Matting
In this paper, we propose a Situational Perception Guided Image Matting (SPG-IM) method that mitigates subjective bias of matting annotations and captures sufficient situational perception information for better global saliency distilled from the visual-to-textual task.
Faster-TAD: Towards Temporal Action Detection with Proposal Generation and Classification in a Unified Network
In this paper, we propose a unified network for TAD, termed Faster-TAD, by re-purposing a Faster-RCNN like architecture.
SEAL: A Large-scale Video Dataset of Multi-grained Spatio-temporally Action Localization
SEAL consists of two kinds of annotations, SEAL Tubes and SEAL Clips.
Personalized Image Aesthetics Assessment with Rich Attributes
To solve the dilemma, we conduct so far, the most comprehensive subjective study of personalized image aesthetics and introduce a new Personalized image Aesthetics database with Rich Attributes (PARA), which consists of 31, 220 images with annotations by 438 subjects.
Self-Distillation from the Last Mini-Batch for Consistency Regularization
Afterwards, the former half mini-batch distills on-the-fly soft targets generated in the previous iteration.
Structured Local Radiance Fields for Human Avatar Modeling
These local radiance fields not only leverage the flexibility of implicit representation in shape and appearance modeling, but also factorize cloth deformations into skeleton motions, node residual translations and the dynamic detail variations inside each individual radiance field.
Adaptive Patch Exiting for Scalable Single Image Super-Resolution
Once the incremental capacity is below the threshold, the patch can exit at the specific layer.
Semantic Distillation Guided Salient Object Detection
Most existing CNN-based salient object detection methods can identify local segmentation details like hair and animal fur, but often misinterpret the real saliency due to the lack of global contextual information caused by the subjectiveness of the SOD task and the locality of convolution layers.
Single-Stage Is Enough: Multi-Person Absolute 3D Pose Estimation
The existing multi-person absolute 3D pose estimation methods are mainly based on two-stage paradigm, i. e., top-down or bottom-up, leading to redundant pipelines with high computation cost.
Simple and Robust Loss Design for Multi-Label Learning with Missing Labels
Multi-label learning in the presence of missing labels (MLML) is a challenging problem.
CRIS: CLIP-Driven Referring Image Segmentation
In addition, we present text-to-pixel contrastive learning to explicitly enforce the text feature similar to the related pixel-level features and dissimilar to the irrelevances.
Ranked #5 on
Referring Expression Segmentation
on RefCOCO+ val
Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation
In this paper, we propose a new framework Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation (DTS-VIBE), to generate 3D human pose and mesh from RGB videos.
Ranked #3 on
3D Human Pose Estimation
on MPI-INF-3DHP
(PA-MPJPE metric)
Pose Refinement with Joint Optimization of Visual Points and Lines
High-precision camera re-localization technology in a pre-established 3D environment map is the basis for many tasks, such as Augmented Reality, Robotics and Autonomous Driving.
Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction
In this paper, we propose a Virtual Multi-modality Foreground Matting (VMFM) method to learn human-object interactive foreground (human and objects interacted with him or her) from a raw RGB image.
Towards Communication-Efficient and Privacy-Preserving Federated Representation Learning
This paper investigates the feasibility of federated representation learning under the constraints of communication cost and privacy protection.
Improving the Robustness of Adversarial Attacks Using an Affine-Invariant Gradient Estimator
As designers of artificial intelligence try to outwit hackers, both sides continue to hone in on AI's inherent vulnerabilities.
The 2nd Anti-UAV Workshop & Challenge: Methods and Results
The 2nd Anti-UAV Workshop \& Challenge aims to encourage research in developing novel and accurate methods for multi-scale object tracking.
Retrieval and Localization with Observation Constraints
The localization pipeline is designed as a coarse-to-fine paradigm.
On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals
It is a consensus that small models perform quite poorly under the paradigm of self-supervised contrastive learning.
View-Guided Point Cloud Completion
This paper presents a view-guided solution for the task of point cloud completion.
Ranked #3 on
Point Cloud Completion
on ShapeNet-ViPC
Generator Pyramid for High-Resolution Image Inpainting
Thus, our model consists of a pyramid of fully convolutional GANs, wherein the content GAN is responsible for completing contents in the lowest-resolution masked image, and each texture GAN is responsible for synthesizing textures in a higher-resolution image.
Perceptual Extreme Super Resolution Network with Receptive Field Block
Third, we alternately use different upsampling methods in the upsampling stage to reduce the high computation complexity and still remain satisfactory performance.
Ranked #1 on
Image Super-Resolution
on DIV8K test - 16x upscaling
Visual Localization Using Semantic Segmentation and Depth Prediction
In this paper, we propose a monocular visual localization pipeline leveraging semantic and depth cues.
Discriminative Multi-modality Speech Recognition
Vision is often used as a complementary modality for audio speech recognition (ASR), especially in the noisy environment where performance of solo audio modality significantly deteriorates.
Ranked #6 on
Audio-Visual Speech Recognition
on LRS3-TED
(using extra training data)
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
Learning to Detect Head Movement in Unconstrained Remote Gaze Estimation in the Wild
To better demonstrate the advantage of our methods, we further propose a new benchmark dataset with the most rich distribution of head-gaze combination reflecting real-world scenarios.
To See in the Dark: N2DGAN for Background Modeling in Nighttime Scene
Due to the deteriorated conditions of \mbox{illumination} lack and uneven lighting, nighttime images have lower contrast and higher noise than their daytime counterparts of the same scene, which limits seriously the performances of conventional background modeling methods.
Dually Supervised Feature Pyramid for Object Detection and Segmentation
Feature pyramid architecture has been broadly adopted in object detection and segmentation to deal with multi-scale problem.
Generative One-Shot Face Recognition
Specifically, we target at building a more effective general face classifier for both normal persons and one-shot persons.
Edge Heuristic GAN for Non-uniform Blind Deblurring
Non-uniform blur, mainly caused by camera shake and motions of multiple objects, is one of the most common causes of image quality degradation.
Large Scale Incremental Learning
We believe this is because of the combination of two factors: (a) the data imbalance between the old and new classes, and (b) the increasing number of visually similar classes.
Ranked #2 on
Incremental Learning
on ImageNet100 - 10 steps
(# M Params metric)
Learning to Count Objects with Few Exemplar Annotations
In this paper, we study the problem of object counting with incomplete annotations.
Revisit Multinomial Logistic Regression in Deep Learning: Data Dependent Model Initialization for Image Recognition
We study in this paper how to initialize the parameters of multinomial logistic regression (a fully connected layer followed with softmax and cross entropy loss), which is widely used in deep neural network (DNN) models for classification problems.
Incremental Classifier Learning with Generative Adversarial Networks
To address these problems, we propose (a) a new loss function to combine the cross-entropy loss and distillation loss, (b) a simple way to estimate and remove the unbalance between the old and new classes , and (c) using Generative Adversarial Networks (GANs) to generate historical data and select representative exemplars during generation.
One-shot Face Recognition by Promoting Underrepresented Classes
First, we build a face feature extraction model, and improve its performance, especially for the persons with very limited training samples, by introducing a regularizer to the cross entropy loss for the multi-nomial logistic regression (MLR) learning.
Model-based Iterative Restoration for Binary Document Image Compression with Dictionary Learning
Experimental results with a variety of document images demonstrate that our method improves the image quality compared with the observed image, and simultaneously improves the compression ratio.
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
In this paper, we design a benchmark task and provide the associated datasets for recognizing face images and link them to corresponding entity keys in a knowledge base.
