Search Results for author:
Found 89 papers, 50 papers with code
Enabling Deep Residual Networks for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) has attracted extensive research attention due to its great flexibility of exploiting large-scale image-level annotation for detector training.
UniAV: Unified Audio-Visual Perception for Multi-Task Video Localization
Video localization tasks aim to temporally locate specific instances in videos, including temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL).
Negative Label Guided OOD Detection with Pretrained Vision-Language Models
In this paper, we propose a novel post hoc OOD detection method, called NegLabel, which takes a vast number of negative labels from extensive corpus databases.
SoftPatch: Unsupervised Anomaly Detection with Noisy Data
Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction.
Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference
To address this issue, we introduce a Multi-class Implicit Neural representation Transformer for unified Anomaly Detection (MINT-AD), which leverages the fine-grained category information in the training stage.
Tuning-Free Image Customization with Image and Text Guidance
To our knowledge, this is the first tuning-free method that concurrently utilizes text and image guidance for image customization in specific regions.
Place Anything into Any Video
This paper introduces a novel and efficient system named Place-Anything, which facilitates the insertion of any object into any video solely based on a picture or text description of the target object or element.
Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt
Unsupervised Anomaly Detection (UAD) with incremental training is crucial in industrial manufacturing, as unpredictable defects make obtaining sufficient labeled data infeasible.
Video Understanding with Large Language Models: A Survey
With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly.
Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning
By pulling the learned features to these semantic anchors, several advantages can be attained: 1) the intra-class compactness and naturally inter-class separability, 2) induced bias or errors from feature learning can be avoided, and 3) robustness to the long-tailed problem.
Real3D-AD: A Dataset of Point Cloud Anomaly Detection
High-precision point cloud anomaly detection is the gold standard for identifying the defects of advancing machining and precision manufacturing.
Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples
Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene.
Referring Video Object Segmentation
Semantic Segmentation
+1
Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models
Pre-trained vision-language models, e. g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning.
Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection
By integrating complementary information from RGB image and depth map, the ability of salient object detection (SOD) for complex and challenging scenes can be improved.
Transferable Decoding with Visual Entities for Zero-Shot Image Captioning
In this paper, we propose ViECap, a transferable decoding model that leverages entity-aware decoding to generate descriptions in both seen and unseen scenarios.
EasyNet: An Easy Network for 3D Industrial Anomaly Detection
3D anomaly detection is an emerging and vital computer vision task in industrial manufacturing (IM).
Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models
Vision-language pre-training (VLP) models have shown vulnerability to adversarial examples in multimodal tasks.
K-Space-Aware Cross-Modality Score for Synthesized Neuroimage Quality Assessment
To further reflect the frequency-specific information from the magnetic resonance imaging principles, both k-space features and vision features are obtained and employed in our comprehensive encoders with a frequency reconstruction penalty.
LaunchpadGPT: Language Model as Music Visualization Designer on Launchpad
To assist and inspire the design of the Launchpad light effect, and provide a more accessible approach for beginners to create music visualization with this instrument, we proposed the LaunchpadGPT model to generate music visualization designs on Launchpad automatically.
LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning
This paper proposes an effective model LLMVA-GEBC (Large Language Model with Video Adapter for Generic Event Boundary Captioning): (1) We utilize a pretrained LLM for generating human-like captions with high quality.
CageViT: Convolutional Activation Guided Efficient Vision Transformer
Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence.
Detecting Out-of-distribution Data through In-distribution Class Prior
In this paper, we show that this assumption makes the above methods incapable when the ID model is trained with class-imbalanced data. Fortunately, by analyzing the causal relations between ID/OOD classes and features, we identify several common scenarios where the OOD-to-ID probabilities should be the ID-class-prior distribution and propose two strategies to modify existing inference-time detection methods: 1) replace the uniform distribution with the ID-class-prior distribution if they explicitly use the uniform distribution; 2) otherwise, reweight their scores according to the similarity between the ID-class-prior distribution and the softmax outputs of the pre-trained model.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Track Anything: Segment Anything Meets Videos
Therefore, in this report, we propose Track Anything Model (TAM), which achieves high-performance interactive tracking and segmentation in videos.
Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems?
This motivates us to study decentralized minimax optimization algorithms for the nonconvex-nonconcave problem.
What makes a good data augmentation for few-shot unsupervised image anomaly detection?
Data augmentation is a promising technique for unsupervised anomaly detection in industrial applications, where the availability of positive samples is often limited due to factors such as commercial competition and sample collection difficulties.
Accelerating Vision-Language Pretraining with Free Language Modeling
FLM successfully frees the prediction rate from the tie-up with the corruption rate while allowing the corruption spans to be customized for each token to be predicted.
Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline
To better adapt to real-life applications, in this paper we focus on the task of dense-localizing audio-visual events, which aims to jointly localize and recognize all audio-visual events occurring in an untrimmed video.
Ranked #1 on
audio-visual event localization
on UnAV-100
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
Our framework is easily extensible to tasks covering visually-grounded language understanding and generation.
On the Stability and Generalization of Triplet Learning
Triplet learning, i. e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e. g., face recognition and person re-identification.
IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing
We realize that the lack of a uniform IM benchmark is hindering the development and usage of IAD methods in real-world applications.
Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore
Besides, we provide a novel model GraphCore via VIIFs that can fast implement unsupervised FSAD training and can improve the performance of anomaly detection.
Deep Industrial Image Anomaly Detection: A Survey
In this paper, we provide a comprehensive review of deep learning-based image anomaly detection techniques, from the perspectives of neural network architectures, levels of supervision, loss functions, metrics and datasets.
Resource-Efficient RGBD Aerial Tracking
However, current research on aerial perception has mainly focused on limited categories, such as pedestrian or vehicle, and most scenes are captured in urban environments from a birds-eye view.
Learning Dual-Fused Modality-Aware Representations for RGBD Tracking
However, some existing RGBD trackers use the two modalities separately and thus some particularly useful shared information between them is ignored.
Towards Continual Adaptation in Industrial Anomaly Detection
We believe that the proposed task and benchmark will be beneficial to the field of AD.
Does Thermal Really Always Matter for RGB-T Salient Object Detection?
In addition, considering the role of thermal modality, we set up different cross-modality interaction mechanisms in the encoding phase and the decoding phase.
Deep Manifold Hashing: A Divide-and-Conquer Approach for Semi-Paired Unsupervised Cross-Modal Retrieval
Hashing that projects data into binary codes has shown extraordinary talents in cross-modal retrieval due to its low storage usage and high query speed.
Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward
The existing method performs well at video segmentation stages but suffers from the problems of dependencies on extra cumbersome models and poor performance at the segment assemblage stage.
Pose-Aided Video-based Person Re-Identification via Recurrent Graph Convolutional Network
Finally, we propose a dual-attention method consisting of node-attention and time-attention to obtain the temporal graph representation from the node embeddings, where the self-attention mechanism is employed to learn the importance of each node and each frame.
Spatial-Temporal Pyramid Graph Reasoning for Action Recognition
Spatial-temporal relation reasoning is a significant yet challenging problem for video action recognition.
Ranked #35 on
Action Recognition
on Something-Something V1
S$^2$Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning
In this paper, we propose a novel semi-supervised framework that allows us to learn contact from monocular images.
Prompting for Multi-Modal Tracking
Multi-modal tracking gains attention due to its ability to be more accurate and robust in complex scenarios compared to traditional RGB-based tracking.
Ranked #8 on
Rgb-T Tracking
on LasHeR
Exploiting Context Information for Generic Event Boundary Captioning
Previous methods only process the information of a single boundary at a time, which lacks utilization of video context information.
VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix
Existing vision-language pre-training (VLP) methods primarily rely on paired image-text datasets, which are either annotated by enormous human labors, or crawled from the internet followed by elaborate data cleaning techniques.
VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization
The tangent transfer creates initial augmented samples for improving corruption robustness.
Semantic-Aware Pretraining for Dense Video Captioning
This report describes the details of our approach for the event dense-captioning task in ActivityNet Challenge 2021.
RGBD Object Tracking: An In-depth Review
Particularly, we are the first to provide depth quality evaluation and analysis of tracking results in depth-friendly scenarios in RGBD tracking.
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
Modeling latent variables with priors and hyperpriors is an essential problem in variational image compression.
Error-based Knockoffs Inference for Controlled Feature Selection
Recently, the scheme of model-X knockoffs was proposed as a promising solution to address controlled feature selection under high-dimensional finite-sample settings.
Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs
Figure skating scoring is challenging because it requires judging the technical moves of the players as well as their coordination with the background music.
Class-Aware Contrastive Semi-Supervised Learning
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization.
A Survey of Visual Sensory Anomaly Detection
In this survey, we are the first one to provide a comprehensive review of visual sensory AD and category into three levels according to the form of anomalies.
Cross-Modality Neuroimage Synthesis: A Survey
This is followed by a stepwise in-depth analysis to evaluate how cross-modality neuroimage synthesis improves the performance of its downstream tasks.
FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform Loss
The proposed method demonstrates the advanced performance in both the quality of our synthesized results under a severely misaligned and unpaired data setting, and better stability than other GAN-based algorithms.
FedMed-GAN: Federated Domain Translation on Unsupervised Cross-Modality Brain Image Synthesis
There is a clear need to launch a federated learning and facilitate the integration of the dispersed data from different institutions.
Meta Distribution Alignment for Generalizable Person Re-Identification
Domain Generalizable (DG) person ReID is a challenging task which trains a model on source domains yet generalizes well on target domains.
Domain Generalization
Generalizable Person Re-identification
+1
GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference
In this paper, we propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net, by leveraging labeled information to guide the learning of unlabeled instances.
Benchmarks for Corruption Invariant Person Re-identification
When deploying person re-identification (ReID) model in safety-critical applications, it is pivotal to understanding the robustness of the model against a diverse array of image corruptions.
Ranked #1 on
Cross-Modal Person Re-Identification
on RegDB-C
(mINP (Visible to Thermal) metric)
Cross-Modal Person Re-Identification
Generalizable Person Re-identification
DepthTrack : Unveiling the Power of RGBD Tracking
RGBD (RGB plus depth) object tracking is gaining momentum as RGBD sensors have become popular in many application fields such as robotics. However, the best RGBD trackers are extensions of the state-of-the-art deep RGB trackers.
Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation
Annotation burden has become one of the biggest barriers to semantic segmentation.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
End-to-End Dense Video Captioning with Parallel Decoding
Dense video captioning aims to generate multiple associated captions with their temporal locations from the video.
Ranked #5 on
Dense Video Captioning
on YouCook2
An Information-theoretic Perspective of Hierarchical Clustering
In this paper, we investigate hierarchical clustering from the \emph{information-theoretic} perspective and formulate a new objective function.
Saliency-Associated Object Tracking
A potential limitation of such trackers is that not all patches are equally informative for tracking.
FREE: Feature Refinement for Generalized Zero-Shot Learning
FREE employs a feature refinement (FR) module that incorporates \textit{semantic$\rightarrow$visual} mapping into a unified generative model to refine the visual features of seen and unseen class samples.
WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations
In this work, we propose an effective weakly-supervised video semantic segmentation pipeline with click annotations, called WeClick, for saving laborious annotating effort by segmenting an instance of the semantic class with only a single click.
GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
To take advantage of the labeled examples and guide unlabeled data learning, we further propose a mask generation module to generate high-quality pseudo masks for the unlabeled data.
Learning 3D Shape Feature for Texture-Insensitive Person Re-Identification
In this paper, rather than relying on texture based information, we propose to improve the robustness of person ReID against clothing texture by exploiting the information of a person's 3D shape.
Ranked #4 on
Person Re-Identification
on PRCC
Brain Image Synthesis With Unsupervised Multivariate Canonical CSCl4Net
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition.
Brain Image Synthesis with Unsupervised Multivariate Canonical CSC$\ell_4$Net
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition.
Tiny Adversarial Mulit-Objective Oneshot Neural Architecture Search
Our work focuses on how to improve the robustness of tiny neural networks without seriously deteriorating of clean accuracy under mobile-level resources.
A Bayesian Federated Learning Framework with Online Laplace Approximation
On the client side, a prior loss that uses the global posterior probabilistic parameters delivered from the server is designed to guide the local training.
Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search
Secondly, a BERT with locality-constrained attention is proposed to obtain representations of descriptions at different scales.
Ranked #15 on
Text based Person Retrieval
on CUHK-PEDES
DepthTrack: Unveiling the Power of RGBD Tracking
This can be explained by the fact that there are no sufficiently large RGBD datasets to 1) train "deep depth trackers" and to 2) challenge RGB trackers with sequences for which the depth cue is essential.
One for More: Selecting Generalizable Samples for Generalizable ReID Model
Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the performance on samples outside the batch.
Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery
For high-dimensional observations in real environment, e. g., Coronal Mass Ejections (CMEs) data, the learning performance of previous methods may be degraded seriously due to the complex non-Gaussian noise and the insufficiency of prior knowledge on variable structure.
A Parallel Down-Up Fusion Network for Salient Object Detection in Optical Remote Sensing Images
In this paper, we propose a novel Parallel Down-up Fusion network (PDF-Net) for SOD in optical RSIs, which takes full advantage of the in-path low- and high-level features and cross-path multi-resolution features to distinguish diversely scaled salient objects and suppress the cluttered backgrounds.
Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification
Secondly, the Conditional Feature Embedding requires the overall feature of a query image to be dynamically adjusted based on the gallery image it matches, while most of the existing methods ignore the reference images.
Ranked #1 on
Person Re-Identification
on CUHK03-C
LSOTB-TIR:A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark
We evaluate and analyze more than 30 trackers on LSOTB-TIR to provide a series of baselines, and the results show that deep trackers achieve promising performance.
Thermal Infrared Object Tracking
Vocal Bursts Intensity Prediction
Dual Distribution Alignment Network for Generalizable Person Re-Identification
Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID), which trains the model using labels from the source domain alone, and then directly adopts the trained model to the target domain without model updating.
Domain Generalization
Generalizable Person Re-identification
3dDepthNet: Point Cloud Guided Depth Completion Network for Sparse Depth and Single Color Image
In this paper, we propose an end-to-end deep learning network named 3dDepthNet, which produces an accurate dense depth image from a single pair of sparse LiDAR depth and color image for robotics and autonomous driving tasks.
Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification
Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level.
Ranked #5 on
Person Re-Identification
on Market-1501
(using extra training data)
Rethinking Temporal Fusion for Video-based Person Re-identification on Semantic and Time Aspect
Recently, the research interest of person re-identification (ReID) has gradually turned to video-based methods, which acquire a person representation by aggregating frame features of an entire video.
Supervised Online Hashing via Similarity Distribution Learning
In this paper, we propose to model the similarity distributions between the input data and the hashing codes, upon which a novel supervised online hashing method, dubbed as Similarity Distribution based Online Hashing (SDOH), is proposed, to keep the intrinsic semantic relationship in the produced Hamming space.
Deep Spectral Clustering using Dual Autoencoder Network
In this paper, we propose a joint learning framework for discriminative embedding and spectral clustering.
Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
Most existing Re-IDentification (Re-ID) methods are highly dependent on precise bounding boxes that enable images to be aligned with each other.
Ranked #2 on
Person Re-Identification
on CUHK03-C
Unsupervised Deep Generative Adversarial Hashing Network
HashGAN consists of three networks, a generator, a discriminator and an encoder.
Trifo-VIO: Robust and Efficient Stereo Visual Inertial Odometry using Points and Lines
In this paper, we present the Trifo Visual Inertial Odometry (Trifo-VIO), a tightly-coupled filtering-based stereo VIO system using both points and lines.
PIRVS: An Advanced Visual-Inertial SLAM System with Flexible Sensor Fusion and Hardware Co-Design
In this paper, we present the PerceptIn Robotics Vision System (PIRVS) system, a visual-inertial computing hardware with embedded simultaneous localization and mapping (SLAM) algorithm.
Dual-reference Face Retrieval
Face retrieval has received much attention over the past few decades, and many efforts have been made in retrieving face images against pose, illumination, and expression variations.
