Search Results for author:
Found 108 papers, 48 papers with code
Generalizable AI-Generated Image Detection Based on Fractal Self-Similarity in the Spectrum
The generalization performance of AI-generated image detection remains a critical challenge.
KwaiChat: A Large-Scale Video-Driven Multilingual Mixed-Type Dialogue Corpus
To mitigate this challenge, we propose a novel task and create a human-to-human video-driven multilingual mixed-type dialogue corpus, termed KwaiChat, containing a total of 93, 209 videos and 246, 080 dialogues, across 4 dialogue types, 30 domains, 4 languages, and 13 topics.
OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images
However, existing OVD methods for remote sensing (RS) images are constrained by small-scale datasets and fail to address the unique challenges of remote sensing interpretation, include oriented object detection and the need for both high precision and real-time performance in diverse scenarios.
Deepfake Detection via Knowledge Injection
Specifically, a knowledge injection module is proposed to learn and inject necessary knowledge into the backbone model, to achieve a more accurate modeling of the distributions of real and fake data.
PACF: Prototype Augmented Compact Features for Improving Domain Adaptive Object Detection
These detectors exhibit higher-variance class-conditional distributions in the target domain than that in the source domain, along with mean shift.
Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning
In this work, we propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner during training, and reparameterizing the learned structure for efficient inference.
Generating Editable Head Avatars with 3D Gaussian GANs
We propose a novel approach that enhances the editability and animation control of 3D head avatars by incorporating 3D Gaussian Splatting (3DGS) as an explicit 3D representation.
TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models
However, most of them fail to tackle with the large variations in the distribution of activations across distinct channels and timesteps, as well as the inconsistent of input between quantization and inference on diffusion models, thus leaving much room for improvement.
Lightweight Spatial Embedding for Vision-based 3D Occupancy Prediction
Finally, TPV Embeddings will interact with each other by Lightweight TPV Interaction module to obtain the Spatial Embedding that is optimal supplementary to BEV features.
ONER: Online Experience Replay for Incremental Anomaly Detection
Specifically, our framework utilizes two types of experiences from past tasks: decomposed prompts and semantic prototypes, addressing both model parameter updates and feature optimization.
A Survey on Data Synthesis and Augmentation for Large Language Models
The success of Large Language Models (LLMs) is inherently linked to the availability of vast, diverse, and high-quality data for training and evaluation.
GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection
In this paper, we identify the drawbacks of previous approaches that limit the geometric quality of BEV representation and propose Radial-Cartesian BEV Sampling (RC-Sampling), which outperforms other feature transformation methods in efficiently generating high-resolution dense BEV representation to restore fine-grained geometric information.
Ranked #7 on
3D Object Detection
on nuScenes Camera Only
GLGait: A Global-Local Temporal Receptive Field Network for Gait Recognition in the Wild
Recently, some Convolution Neural Networks (ConvNets) based methods have been proposed to address the issue of gait recognition in the wild.
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
To address these issues, we propose a novel non-uniform quantizer, dubbed the Adaptive Logarithm AdaLog (AdaLog) quantizer.
FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection
In recent years, several cross-modal distillation methods have been proposed to transfer beneficial information from teacher models to student models, with the aim of enhancing performance.
MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detection
However, the detection pre-training remains unexplored in remote sensing scenes.
Semantic Enhanced Few-shot Object Detection
As a result, our method allows each novel class to construct a compact feature space without being confused with similar base classes.
Leveraging Predicate and Triplet Learning for Scene Graph Generation
We observe that visual variations within the identical triplet are relatively small and certain relation cues are shared in the same type of triplet, which can potentially facilitate the relation learning in SGG.
4Diffusion: Multi-view Video Diffusion Model for 4D Generation
We first design a unified diffusion model tailored for multi-view video generation by incorporating a learnable motion module into a frozen 3D-aware diffusion model to capture multi-view spatial-temporal correlations.
3D Face Modeling via Weakly-supervised Disentanglement Network joint Identity-consistency Prior
Generative 3D face models featuring disentangled controlling factors hold immense potential for diverse applications in computer vision and computer graphics.
AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation
Adversarial example detection, which can be conveniently applied in many scenarios, is important in the area of adversarial defense.
LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning
Based on this paradigm, we propose a new perspective to defeat trigger reverse engineering by manipulating the classification confidence of backdoor samples.
YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images
2) Small object size leads to insufficient information for effective detection.
Understanding Heterophily for Graph Neural Networks
Firstly, we show that by applying a GC operation, the separability gains are determined by two factors, i. e., the Euclidean distance of the neighborhood distributions and $\sqrt{\mathbb{E}\left[\operatorname{deg}\right]}$, where $\mathbb{E}\left[\operatorname{deg}\right]$ is the averaged node degree.
Generic Knowledge Boosted Pre-training For Remote Sensing Images
Deep learning models are essential for scene classification, change detection, land cover segmentation, and other remote sensing image understanding tasks.
Towards Generalizable Referring Image Segmentation via Target Prompt and Visual Coherence
Referring image segmentation (RIS) aims to segment objects in an image conditioning on free-from text descriptions.
DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection
Furthermore, these methods face a more formidable challenge in achieving consistent classification and localization in the target domain compared to the source domain.
ActiveDC: Distribution Calibration for Active Finetuning
Firstly, we select samples for annotation by optimizing the distribution similarity between the subset to be selected and the entire unlabeled pool in continuous space.
HIPTrack: Visual Tracking with Historical Prompts
In this paper, we show that by providing a tracker that follows Siamese paradigm with precise and updated historical information, a significant performance improvement can be achieved with completely unchanged parameters.
Ranked #4 on
Visual Object Tracking
on NeedForSpeed
Improving Multi-Person Pose Tracking with A Confidence Network
Specifically, the keypoint confidence network is designed to determine whether each keypoint is occluded, and it is incorporated into the pose estimation module.
Incremental Object Detection with CLIP
In contrast to the incremental classification task, the incremental detection task is characterized by the presence of data ambiguity, as an image may have differently labeled bounding boxes across multiple continuous learning stages.
Context-Enhanced Detector For Building Detection From Remote Sensing Images
Our approach utilizes a three-stage cascade structure to enhance the extraction of contextual information and improve building detection accuracy.
CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding
To address these problems, we propose a context-enhanced masked image modeling method (CtxMIM), a simple yet efficient MIM-based self-supervised learning for remote sensing image understanding.
HiT: Building Mapping with Hierarchical Transformers
The polygon head formulates a building polygon as serialized vertices with the bidirectional characteristic, a simple and elegant polygon representation avoiding the start or end vertex hypothesis.
Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction
In our framework, a triplet calibration loss is first presented to regularize the representations of diverse triplets and to simultaneously excavate the unseen triplets in incompletely annotated training scene graphs.
Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection
Anomaly detection (AD), aiming to find samples that deviate from the training distribution, is essential in safety-critical applications.
RFDforFin: Robust Deep Forgery Detection for GAN-generated Fingerprint Images
In this paper, we propose the first deep forgery detection approach for fingerprint images, which combines unique ridge features of fingerprint and generation artifacts of the GAN-generated images, to the best of our knowledge.
SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection
In this paper, we propose Semantic-Aware BEV Pooling (SA-BEVPool), which can filter out background information according to the semantic segmentation of image features and transform image features into semantic-aware BEV features.
Ranked #10 on
3D Object Detection
on nuScenes Camera Only
Common Knowledge Learning for Generating Transferable Adversarial Examples
Specifically, to reduce the model-specific features and obtain better output distributions, we construct a multi-teacher framework, where the knowledge is distilled from different teacher architectures into one student network.
Denoising Diffusion Autoencoders are Unified Self-supervised Learners
Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training.
Learning Discriminative Representations for Skeleton Based Action Recognition
Furthermore, FR Head could be imposed on different stages of GCNs to build a multi-level refinement for stronger supervision.
BiSVP: Building Footprint Extraction via Bidirectional Serialized Vertex Prediction
Extracting building footprints from remote sensing images has been attracting extensive attention recently.
Heterophily-Aware Graph Attention Network
In this paper, we firstly propose a heterophily-aware attention scheme and reveal the benefits of modeling the edge heterophily, i. e., if a GNN assigns different weights to edges according to different heterophilic types, it can learn effective local attention patterns, which enable nodes to acquire appropriate information from distinct neighbors.
An Empirical Study on Multi-Domain Robust Semantic Segmentation
How to effectively leverage the plentiful existing datasets to train a robust and high-performance model is of great significance for many practical applications.
Binary Graph Convolutional Network with Capacity Exploration
The current success of Graph Neural Networks (GNNs) usually relies on loading the entire attributed graph for processing, which may not be satisfied with limited memory resources, especially when the attributed graph is large.
Exploring Effective Knowledge Transfer for Few-shot Object Detection
For the high-shot regime, we propose to use the knowledge learned from ImageNet as guidance for the feature learning in the fine-tuning stage, which will implicitly align the distributions of the novel classes.
D$^{\bf{3}}$: Duplicate Detection Decontaminator for Multi-Athlete Tracking in Sports Videos
In this paper, the duplicate detection is newly and precisely defined as occlusion misreporting on the same athlete by multiple detection boxes in one frame.
Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embedding
Extensive experiments demonstrate that our RE-GNN can effectively and efficiently handle the heterogeneous graphs and can be applied to various homogeneous GNNs.
Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles
Video Anomaly Detection (VAD) is an important topic in computer vision.
Ranked #7 on
Anomaly Detection
on ShanghaiTech
SparseTT: Visual Tracking with Sparse Transformers
In this paper, we relieve this issue with a sparse attention mechanism by focusing the most relevant information in the search regions, which enables a much accurate tracking.
PanFormer: a Transformer Based Model for Pan-sharpening
Pan-sharpening aims at producing a high-resolution (HR) multi-spectral (MS) image from a low-resolution (LR) multi-spectral (MS) image and its corresponding panchromatic (PAN) image acquired by a same satellite.
RealGait: Gait Recognition for Person Re-Identification
Given that our experimental results show that current gait recognition approaches designed under data collected in controlled scenarios are inappropriate for real surveillance scenarios, we propose a novel gait recognition method, called RealGait.
Lagrange Motion Analysis and View Embeddings for Improved Gait Recognition
Gait is considered the walking pattern of human body, which includes both shape and motion cues.
Segmentation-Reconstruction-Guided Facial Image De-occlusion
The proposed model consists of a 3D face reconstruction module, a face segmentation module, and an image generation module.
Will You Ever Become Popular? Learning to Predict Virality of Dance Clips
Therefore, virality prediction from dance challenges is of great commercial value and has a wide range of applications, such as smart recommendation and popularity promotion.
Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast
Moreover, armed with our method, we increase the segmentation mIoU of EPS from 70. 8% to 73. 6%, achieving new state-of-the-art.
Ranked #15 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
Unsupervised Cycle-consistent Generative Adversarial Networks for Pan-sharpening
Most of existing methods fall into the supervised learning framework in which they down-sample the multi-spectral (MS) and panchromatic (PAN) images and regard the original MS images as ground truths to form training samples.
iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization
Differentiable ARchiTecture Search (DARTS) uses a continuous relaxation of network representation and dramatically accelerates Neural Architecture Search (NAS) by almost thousands of times in GPU-day.
Ranked #9 on
Neural Architecture Search
on CIFAR-10
Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchy
In this paper, we explore effective mechanisms to boost both of them from the perspective of network hierarchy, where a typical network can be hierarchically divided into output stage, intermediate stage and input stage.
Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning
Fine-grained action recognition is attracting increasing attention due to the emerging demand of specific action understanding in real-world applications, whereas the data of rare fine-grained categories is very limited.
Silhouette based View embeddings for Gait Recognition under Multiple Views
Gait recognition under multiple views is an important computer vision and pattern recognition task.
Cross-View Gait Recognition With Deep Universal Linear Embeddings
Furthermore, a novel framework based on convolutional variational autoencoder and deep Koopman embedding is proposed to approximate the Koopman operators, which is used as dynamical features from the linearized embedding space for cross-view gait recognition.
Weakly-Supervised Photo-realistic Texture Generation for 3D Face Reconstruction
Missing textures in the incomplete UV map are further full-filled by the UV generator.
Pixel Sampling for Style Preserving Face Pose Editing
The existing auto-encoder based face pose editing methods primarily focus on modeling the identity preserving ability during pose synthesis, but are less able to preserve the image style properly, which refers to the color, brightness, saturation, etc.
Visual Grounding with Transformers
In this paper, we propose a transformer based approach for visual grounding.
Magnifying Subtle Facial Motions for Effective 4D Expression Recognition
In this paper, an effective pipeline to automatic 4D Facial Expression Recognition (4D FER) is proposed.
A Perceptual Distortion Reduction Framework: Towards Generating Adversarial Examples with High Perceptual Quality and Attack Success Rate
This portion of distortions, which is induced by unnecessary modifications and lack of proper perceptual distortion constraint, is the target of the proposed framework.
STMTrack: Template-free Visual Tracking with Space-time Memory Networks
Boosting performance of the offline trained siamese trackers is getting harder nowadays since the fixed information of the template cropped from the first frame has been almost thoroughly mined, but they are poorly capable of resisting target appearance changes.
Ranked #3 on
Visual Object Tracking
on OTB-2015
MRDet: A Multi-Head Network for Accurate Oriented Object Detection in Aerial Images
Objects in aerial images usually have arbitrary orientations and are densely located over the ground, making them extremely challenge to be detected.
Semi-supervised Hyperspectral Image Classification with Graph Clustering Convolutional Networks
To further lift the classification performance, in this work we propose a graph convolution network (GCN) based framework for HSI classification that uses two clustering operations to better exploit multi-hop node correlations and also effectively reduce graph size.
PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection
LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects.
Ranked #4 on
3D Object Detection
on KITTI Cars Hard val
PGMAN: An Unsupervised Generative Multi-adversarial Network for Pan-sharpening
However, since there are no intended HR MS images as references for learning, almost all of the existing methods down-sample the MS and PAN images and regard the original MS images as targets to form a supervised setting for training.
PSGCNet: A Pyramidal Scale and Global Context Guided Network for Dense Object Counting in Remote Sensing Images
Object counting, which aims to count the accurate number of object instances in images, has been attracting more and more attention.
Bi-GCN: Binary Graph Convolutional Network
Graph Neural Networks (GNNs) have achieved tremendous success in graph representation learning.
ARM: A Confidence-Based Adversarial Reweighting Module for Coarse Semantic Segmentation
Experiments on standard datasets shows our ARM can bring consistent improvements for both coarse annotations and fine annotations.
Counting from Sky: A Large-scale Dataset for Remote Sensing Object Counting and A Benchmark Method
Object counting, whose aim is to estimate the number of objects from a given image, is an important and challenging computation task.
Co-Saliency Detection with Co-Attention Fully Convolutional Network
Co-saliency detection aims to detect common salient objects from a group of relevant images.
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited.
Ranked #18 on
Few-Shot Object Detection
on MS-COCO (30-shot)
Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification
Video-based person re-identification (Re-ID) is an important computer vision task.
Cycle-CNN for Colorization towards Real Monochrome-Color Camera Systems
We present a new CNN model, named cycle CNN, which can directly use the real data from monochrome-color camera systems for training.
CNN-based Density Estimation and Crowd Counting: A Survey
Through our analysis, we expect to make reasonable inference and prediction for the future development of crowd counting, and meanwhile, it can also provide feasible solutions for the problem of object counting in other fields.
Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
Thanks to this coarse-to-fine feature adaptation, domain knowledge in foreground regions can be effectively transferred.
From W-Net to CDGAN: Bi-temporal Change Detection via Deep Learning Techniques
Traditional change detection methods usually follow the image differencing, change feature extraction and classification framework, and their performance is limited by such simple image domain differencing and also the hand-crafted features.
Fake Generated Painting Detection via Frequency Analysis
With the development of deep neural networks, digital fake paintings can be generated by various style transfer algorithms. To detect the fake generated paintings, we analyze the fake generated and real paintings in Fourier frequency domain and observe statistical differences and artifacts.
Counting dense objects in remote sensing images
Significant efforts have been made to address this problem and achieve great progress, yet counting number of ground objects from remote sensing images is barely studied.
A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision.
Distraction-Aware Feature Learning for Human Attribute Recognition via Coarse-to-Fine Attention Mechanism
Recently, Human Attribute Recognition (HAR) has become a hot topic due to its scientific challenges and application potentials, where localizing attributes is a crucial stage but not well handled.
Learning Spatial Fusion for Single-Shot Object Detection
Pyramidal feature representation is the common practice to address the challenge of scale variation in object detection.
Ranked #148 on
Object Detection
on COCO test-dev
(using extra training data)
Learning a Deep Convolutional Network for Colorization in Monochrome-Color Dual-Lens System
To get high-quality color images, it is desired to colorize the gray image with the color image as reference.
Adaptive NMS: Refining Pedestrian Detection in a Crowd
Pedestrian detection in a crowd is a very challenging issue.
Ranked #18 on
Object Detection
on CrowdHuman (full body)
A Temporal Attentive Approach for Video-Based Pedestrian Attribute Recognition
In this paper, we first tackle the problem of pedestrian attribute recognition by video-based approach.
Learning Continuous Face Age Progression: A Pyramid of GANs
The two underlying requirements of face age progression, i. e. aging accuracy and identity permanence, are not well studied in the literature.
Attentive Relational Networks for Mapping Images to Scene Graphs
Scene graph generation refers to the task of automatically mapping an image into a semantic structural graph, which requires correctly labeling each extracted object and their interaction relationships.
Expressiveness in Deep Reinforcement Learning
Based on our observations, we formally define expressiveness of the state extractor as the rank of the matrix composed by representations.
stagNet: An Attentive Semantic RNN for Group Activity Recognition
Group activity recognition plays a fundamental role in a variety of applications, e. g. sports video analysis and intelligent surveillance.
PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening
This paper addresses the problem of remote sensing image pan-sharpening from the perspective of generative adversarial learning.
Adversarial Binary Coding for Efficient Person Re-identification
Specifically, instead of learning explicit projections or adding fully-connected mapping layers, the proposed Adversarial Binary Coding (ABC) framework guides the extraction of binary codes implicitly and effectively.
Road Extraction by Deep Residual U-Net
Road extraction from aerial images has been a hot research topic in the field of remote sensing image analysis.
Learning Face Age Progression: A Pyramid Architecture of GANs
The two underlying requirements of face age progression, i. e. aging accuracy and identity permanence, are not well studied in the literature.
Feature Map Pooling for Cross-View Gait Recognition Based on Silhouette Sequence Images
In this paper, we develop a novel convolutional neural network based approach to extract and aggregate useful information from gait silhouette sequence images instead of simply representing the gait process by averaging silhouette images.
Visual and Textual Sentiment Analysis Using Deep Fusion Convolutional Neural Networks
Sentiment analysis is attracting more and more attentions and has become a very hot research topic due to its potential applications in personalized recommendation, opinion mining, etc.
Receptive Field Block Net for Accurate and Fast Object Detection
Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from high computational costs.
Remote Sensing Image Fusion Based on Two-stream Fusion Network
Unlike previous CNN based methods that consider pan-sharpening as a super resolution problem and perform pan-sharpening in pixel level, the proposed TFNet aims to fuse PAN and MS images in feature level and reconstruct the pan-sharpened image from the fused features.
Fast Person Re-Identification via Cross-Camera Semantic Binary Transformation
Numerous methods have been proposed for person re-identification, most of which however neglect the matching efficiency.
Zero-Shot Action Recognition With Error-Correcting Output Codes
Our ZSECOC equips the conventional ECOC with the additional capability of ZSAR, by addressing the domain shift problem.
Ranked #4 on
Zero-Shot Action Recognition
on Olympics
Binary Coding for Partial Action Analysis With Limited Observation Ratios
Extensive experiments on four realistic action datasets in terms of three tasks (i. e., partial action retrieval, recognition and prediction) clearly show the superiority of PRBC over the state-of-the-art methods, along with significantly reduced memory load and computational costs during the online test.
Face Aging Effect Simulation using Hidden Factor Analysis Joint Sparse Representation
Face aging simulation has received rising investigations nowadays, whereas it still remains a challenge to generate convincing and natural age-progressed face images.
