Search Results for author:
Found 136 papers, 54 papers with code
Star-Transformer
Although Transformer has achieved great successes on many NLP tasks, its heavy structure with fully-connected attention connections leads to dependencies on large training data.
Ranked #13 on
Sentiment Analysis
on SST-5 Fine-grained classification
Named Entity Recognition (NER)
Natural Language Inference
+2
BERT-ATTACK: Adversarial Attack Against BERT Using BERT
Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods.
Pose-Normalized Image Generation for Person Re-identification
Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations.
DSOD: Learning Deeply Supervised Object Detectors from Scratch
State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets like ImageNet, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks.
Object Detection from Scratch with Deep Supervision
Thus, a better solution to handle these critical problems is to train object detectors from scratch, which motivates our proposed method.
Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure.
2D Pose Estimation
3D Multi-Person Pose Estimation (absolute)
+4
Arbitrary-Oriented Scene Text Detection via Rotation Proposals
This paper introduces a novel rotation-based framework for arbitrary-oriented text detection in natural scene images.
Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study
The experimental results indicate that the performance of baselines on CTR datasets is not as good as that on English datasets due to the characteristics of Chinese texts that are quite different from the Latin alphabet.
BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
Multiple datasets and open challenges for object detection have been introduced in recent years.
Ranked #1 on
Object Detection
on BigDetection val
Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition
Inspired by the fact that humans can generalize to know how to write characters unseen before if they have learned stroke orders of some characters, we propose a stroke-based method by decomposing each character into a sequence of strokes, which are the most basic units of Chinese characters.
Scene Text Telescope: Text-Focused Scene Image Super-Resolution
Image super-resolution, which is often regarded as a preprocessing procedure of scene text recognition, aims to recover the realistic features from a low-resolution text image.
Image Super-Resolution
Optical Character Recognition (OCR)
+2
Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
However, the recognition of low-resolution scene text images remains a challenge.
Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning
However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few methods have been proposed for Chinese Text Recognition (CTR).
Orientation-Independent Chinese Text Recognition in Scene Images
We conduct experiments on a scene dataset for benchmarking Chinese text recognition, and the results demonstrate that the proposed method can indeed improve performance through disentangling content and orientation information.
DeepSFM: Structure From Motion Via Deep Bundle Adjustment
The explicit constraints on both depth (structure) and pose (motion), when combined with the learning components, bring the merit from both traditional BA and emerging deep learning technology.
Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models
Human and metrics evaluation on both LSTM models and BERT Transformer models on multiple datasets show that our algorithms outperform prior hierarchical explanation algorithms.
MEAL: Multi-Model Ensemble via Adversarial Learning
In this paper, we present a method for compressing large, complex trained ensembles into a single network, where knowledge from a variety of trained deep neural networks (DNNs) is distilled and transferred to a single DNN.
Neural Pose Transfer by Spatially Adaptive Instance Normalization
Pose transfer has been studied for decades, in which the pose of a source mesh is applied to a target mesh.
Model-based Deep Hand Pose Estimation
For the first time, we show that embedding such a non-linear generative process in deep learning is feasible for hand pose estimation.
Multi-level Semantic Feature Augmentation for One-shot Learning
In semantic space, we search for related concepts, which are then projected back into the image feature spaces by the decoder portion of the TriNet.
Progressive Coordinate Transforms for Monocular 3D Object Detection
Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment.
SUPS: A Simulated Underground Parking Scenario Dataset for Autonomous Driving
However, there is a lack of underground parking scenario datasets with multiple sensors and well-labeled images that support both SLAM tasks and perception tasks, such as semantic segmentation and parking slot detection.
LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling
Recent progress in 4D implicit representation focuses on globally controlling the shape and motion with low dimensional latent vectors, which is prone to missing surface details and accumulating tracking error.
Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions
Most existing point cloud upsampling methods have roughly three steps: feature extraction, feature expansion and 3D coordinate prediction.
Is normalization indispensable for training deep neural network?
In this paper, we study what would happen when normalization layers are removed from the network, and show how to train deep neural networks without normalization layers and without performance degradation.
Learning to score the figure skating sports videos
This paper targets at learning to score the figure skating sports videos.
Temporal Context Aggregation for Video Retrieval with Contrastive Learning
The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events, etc.
Ranked #6 on
Video Retrieval
on FIVR-200K
Dynamic Graph Message Passing Networks for Visual Recognition
A fully-connected graph, such as the self-attention operation in Transformers, is beneficial for such modelling, however, its computational overhead is prohibitive.
CODA: Counting Objects via Scale-aware Adversarial Density Adaption
Extensive experiments demonstrate that our network produces much better results on unseen datasets compared with existing counting adaption models.
Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestalt
Unfortunately, the representation learned by SketchRNN is primarily for the generation tasks, rather than the other tasks of recognition and retrieval of sketches.
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
The objective of this paper is to learn context- and depth-aware feature representation to solve the problem of monocular 3D object detection.
Ranked #13 on
Monocular 3D Object Detection
on KITTI Cars Moderate
Learning Dynamic Alignment via Meta-filter for Few-shot Learning
Our insight is that these methods would lead to poor adaptation with redundant matching, and leveraging channel-wise adjustment is the key to well adapting the learned knowledge to new classes.
SGM3D: Stereo Guided Monocular 3D Object Detection
Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image.
Exploring Efficient Few-shot Adaptation for Vision Transformers
Essentially, despite ViTs have been shown to enjoy comparable or even better performance on other vision tasks, it is still very nontrivial to efficiently finetune the ViTs in real-world FSL scenarios.
Joint Parsing and Generation for Abstractive Summarization
If generating a word can introduce an erroneous relation to the summary, the behavior must be discouraged.
Ranked #27 on
Text Summarization
on GigaWord
The Image Local Autoregressive Transformer
To address these limitations, we propose a novel model -- image Local Autoregressive Transformer (iLAT), to better facilitate the locally guided image synthesis.
GAT-COBO: Cost-Sensitive Graph Neural Network for Telecom Fraud Detection
Extensive experiments on two real-world telecom fraud detection datasets demonstrate that our proposed method is effective for the graph imbalance problem, outperforming the state-of-the-art GNNs and GNN-based fraud detectors.
Co-Attention Aligned Mutual Cross-Attention for Cloth-Changing Person Re-Identification
In this paper, we first design a novel Shape Semantics Embedding (SSE) module to encode body shape semantic information, which is one of the essential clues to distinguish pedestrians when their clothes change.
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification
In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial information, short-term motion, as well as long-term temporal clues in the videos.
Cost Sensitive GNN-based Imbalanced Learning for Mobile Social Network Fraud Detection
But the imbalance problem in the aforementioned data, which could severely hinder the effectiveness of fraud detectors based on graph neural networks(GNN), has hardly been addressed in previous work.
Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge
To this end, we propose a novel approach for empathetic response generation, which incorporates an adaptive module for commonsense knowledge selection to ensure consistency between the generated empathetic responses and the speaker's situation.
Repositioning the Subject within Image
Our research reveals that the fundamental sub-tasks of subject repositioning, which include filling the void left by the repositioned subject, reconstructing obscured portions of the subject and blending the subject to be consistent with surrounding areas, can be effectively reformulated as a unified, prompt-guided inpainting task.
A Multi-task Neural Approach for Emotion Attribution, Classification and Summarization
However, the sparsity of emotional expressions in the videos poses an obstacle to visual emotion analysis.
Spatial Mixture Models with Learnable Deep Priors for Perceptual Grouping
Different from existing methods, the proposed method disentangles the attributes of an object into ``shape'' and ``appearance'' which are modeled separately by the mixture weights and the mixture components.
Vocabulary-informed Zero-shot and Open-set Learning
Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of labels.
FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients
The implementation of FedRA is straightforward and can be seamlessly integrated into any transformer-based model without the need for further modification to the original model.
Local Slot Attention for Vision-and-Language Navigation
Since the attention mechanism in the transformer architecture can better integrate inter- and intra-modal information of vision and language.
Raven's Progressive Matrices Completion with Latent Gaussian Process Priors
In this paper we aim to solve the latter one by proposing a deep latent variable model, in which multiple Gaussian processes are employed as priors of latent variables to separately learn underlying abstract concepts from RPMs; thus the proposed model is interpretable in terms of concept-specific latent variables.
Compositional Law Parsing with Latent Random Functions
The automatic parsing of these laws indicates the model's ability to understand the scene, which makes law parsing play a central role in many visual tasks.
Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems
Finally, we conduct experiments to illustrate the interpretability of CRAB in concept learning, answer selection, and global rule abstraction.
One-shot Federated Learning without Server-side Training
Federated Learning (FL) has recently made significant progress as a new machine learning paradigm for privacy protection.
Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning
In this paper, we propose a federated adaptive prompt tuning algorithm, FedAPT, for multi-domain collaborative image classification with powerful foundation models, like CLIP.
Multi-to-Single Knowledge Distillation for Point Cloud Semantic Segmentation
In this paper, we propose a novel multi-to-single knowledge distillation framework for the 3D point cloud semantic segmentation task to boost the performance of those hard classes.
Knowledge-Guided Object Discovery with Acquired Deep Impressions
The proposed ADI framework focuses on the acquisition and utilization of knowledge, and is complementary to existing deep generative models proposed for compositional scene representation.
SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners
In this paper, we proposed a novel filter pruning for convolutional neural networks compression, namely spectral clustering filter pruning with soft self-adaption manners (SCSP).
Dual Skipping Networks
Inspired by the recent neuroscience studies on the left-right asymmetry of the human brain in processing low and high spatial frequency information, this paper introduces a dual skipping network which carries out coarse-to-fine object categorization.
Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks
In this paper, we study the challenging problem of categorizing videos according to high-level semantics such as the existence of a particular human action or a complex event.
Vocabulary-informed Extreme Value Learning
To solve this problem, we propose the Extreme Value Learning (EVL) formulation to learn the mapping from visual feature to semantic space.
DeepSkeleton: Skeleton Map for 3D Human Pose Regression
For the first time, we show that training regression network from skeleton map alone is capable of meeting the performance of state-of-theart 3D human pose estimation works.
Recent Advances in Zero-shot Recognition
With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data.
Multi-scale Deep Learning Architectures for Person Re-identification
Our model is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching.
A Jointly Learned Deep Architecture for Facial Attribute Analysis and Face Detection in the Wild
Facial attribute analysis in the real world scenario is very challenging mainly because of complex face variations.
Modeling Multimodal Clues in a Hybrid Deep Learning Framework for Video Classification
More specifically, we utilize three Convolutional Neural Networks (CNNs) operating on appearance, motion and audio signals to extract their corresponding features.
Semi-Latent GAN: Learning to generate and modify facial images from attributes
Generating and manipulating human facial images using high-level attributal controls are important and interesting problems.
Weakly Supervised Dense Video Captioning
This paper focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences.
Iterative Object and Part Transfer for Fine-Grained Recognition
On both datasets, we achieve better results than many state-of-the-art approaches, including a few using oracle (manually annotated) bounding boxes in the test images.
Evolving Boxes for Fast Vehicle Detection
We perform fast vehicle detection from traffic surveillance cameras.
Learning to Point and Count
This paper proposes the problem of point-and-count as a test case to break the what-and-where deadlock.
Fusing Multi-Stream Deep Networks for Video Classification
A multi-stream framework is proposed to fully utilize the rich multimodal information in videos.
Evaluating Two-Stream CNN for Video Classification
In this paper, we conduct an in-depth study to investigate important implementation options that may affect the performance of deep nets on video classification.
Do More Dropouts in Pool5 Feature Maps for Better Object Detection
In these fields, the outputs of all layers of CNNs are usually considered as a high dimensional feature vector extracted from an input image and the correspondence between finer level feature vectors and concepts that the input image contains is all-important.
Top-Down Tree Structured Text Generation
Text generation is a fundamental building block in natural language processing tasks.
Learning the Compositional Spaces for Generalized Zero-shot Learning
This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time.
Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network
Additionally, to study the tasks of sketch-based hairstyle retrieval, this paper contributes a new instance-level photo-sketch dataset - Hairstyle Photo-Sketch dataset, which is composed of 3600 sketches and photos, and 2400 sketch-photo pairs.
PRUNING IN TRAINING: LEARNING AND RANKING SPARSE CONNECTIONS IN DEEP CONVOLUTIONAL NETWORKS
This paper proposes a Pruning in Training (PiT) framework of learning to reduce the parameter size of networks.
VOCABULARY-INFORMED VISUAL FEATURE AUGMENTATION FOR ONE-SHOT LEARNING
Besides directly augmenting image features, we transform the image features to semantic space using the encoder and perform the data augmentation.
Weakly Supervised Semantic Segmentation for Social Images
Image semantic segmentation is the task of partitioning image into several regions based on semantic concepts.
Multiple Granularity Descriptors for Fine-Grained Categorization
Fine-grained categorization, which aims to distinguish subordinate-level categories such as bird species or dog breeds, is an extremely challenging task.
Question Guided Modular Routing Networks for Visual Question Answering
Particularly, The QGMRN is composed of visual, textual and routing network.
Towards Instance-level Image-to-Image Translation
The proposed INIT exhibits three import advantages: (1) the instance-level objective loss can help learn a more accurate reconstruction and incorporate diverse attributes of objects; (2) the styles used for target domain of local/global areas are from corresponding spatial regions in source domain, which intuitively is a more reasonable mapping; (3) the joint training process can benefit both fine and coarse granularity and incorporates instance information to improve the quality of global translation.
Correlative Multi-Label Multi-Instance Image Annotation
The cross-level label coherence en-codes the consistency between the labels at the image leveland the labels at the region level.
Fast Color Constancy with Patch-wise Bright Pixels
In this paper, a learning-free color constancy algorithm called the Patch-wise Bright Pixels (PBP) is proposed.
Multi-Scale Self-Attention for Text Classification
In this paper, we introduce the prior knowledge, multi-scale structure, into self-attention modules.
Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition
Considering the phenomenon of uneven data distribution and lack of samples is common in real-world scenarios, we further evaluate several tasks of few-shot expression learning by virtue of our F2ED, which are to recognize the facial expressions given only few training instances.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection
We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation.
MOTS: Multiple Object Tracking for General Categories Based On Few-Shot Method
Most modern Multi-Object Tracking (MOT) systems typically apply REID-based paradigm to hold a balance between computational efficiency and performance.
Long-Term Cloth-Changing Person Re-identification
Specifically, we consider that under cloth-changes, soft-biometrics such as body shape would be more reliable.
A New Screening Method for COVID-19 based on Ocular Feature Recognition by Machine Learning Tools
After more than four months study, we found that the confirmed cases of COVID-19 present the consistent ocular pathological symbols; and we propose a new screening method of analyzing the eye-region images, captured by common CCD and CMOS cameras, could reliably make a rapid risk screening of COVID-19 with very high accuracy.
M3Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia Screening from CT Imaging
To counter the outbreak of COVID-19, the accurate diagnosis of suspected cases plays a crucial role in timely quarantine, medical treatment, and preventing the spread of the pandemic.
Nonlinear Monte Carlo Method for Imbalanced Data Learning
and the mean value of loss function is used as the empirical risk by Law of Large Numbers (LLN).
A Generic Object Re-identification System for Short Videos
Short video applications like TikTok and Kwai have been a great hit recently.
Learning Compositional Representation for 4D Captures with Neural ODE
To model the motion, a neural Ordinary Differential Equation (ODE) is trained to update the initial state conditioned on the learned motion code, and a decoder takes the shape code and the updated state code to reconstruct the 3D model at each time stamp.
Delving into Data: Effectively Substitute Training for Black-box Attack
Previous substitute training approaches focus on stealing the knowledge of the target model based on real training data or synthetic data, without exploring what kind of data can further improve the transferability between the substitute and target models.
Rapid COVID-19 Risk Screening by Eye-region Manifestations
It is still nontrivial to develop a new fast COVID-19 screening method with the easier access and lower cost, due to the technical and cost limitations of the current testing methods in the medical resource-poor districts.
SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation
The concatenation of the observed point cloud and symmetric one reconstructs a coarse object shape, thus facilitating object center (3D translation) and 3D size estimation.
The Report on China-Spain Joint Clinical Testing for Rapid COVID-19 Risk Screening by Eye-region Manifestations
The image-level performance of COVID-19 prescreening model in the China-Spain multicenter study achieved an AUC of 0. 913 (95% CI, 0. 898-0. 927), with a sensitivity of 0. 695 (95% CI, 0. 643-0. 748), a specificity of 0. 904 (95% CI, 0. 891 -0. 919), an accuracy of 0. 875(0. 861-0. 889), and a F1 of 0. 611(0. 568-0. 655).
{\mathcal{P}^2}: A Plan-and-Pretrain Approach for Knowledge Graph-to-Text Generation
Text verbalization of knowledge graphs is an important problem with wide application to natural language generation (NLG) systems.
DeepEnFM: Deep neural networks with Encoder enhanced Factorization Machine
Instead of learning the cross features directly, DeepEnFM adopts the Transformer encoder as a backbone to align the feature embeddings with the clues of other fields.
Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints
When observing a visual scene that contains multiple objects from multiple viewpoints, humans are able to perceive the scene in a compositional way from each viewpoint, while achieving the so-called "object constancy" across different viewpoints, even though the exact viewpoints are untold.
The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection
Low-cost monocular 3D object detection plays a fundamental role in autonomous driving, whereas its accuracy is still far from satisfactory.
Compositional Scene Representation Learning via Reconstruction: A Survey
In this survey, we first outline the current progress on reconstruction-based compositional scene representation learning with deep neural networks, including development history and categorizations of existing methods from the perspectives of the modeling of visual scenes and the inference of scene representations; then provide benchmarks, including an open source toolbox to reproduce the benchmark experiments, of representative methods that consider the most extensively studied problem setting and form the foundation for other methods; and finally discuss the limitations of existing methods and future directions of this research topic.
H4D: Human 4D Modeling by Learning Neural Compositional Representation
A simple yet effective linear motion model is proposed to provide a rough and regularized motion estimation, followed by per-frame compensation for pose and geometry details with the residual encoded in the auxiliary code.
QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation
To this end, this paper proposes a novel model of learning to Quantize, Scrabble, and Craft (QS-Craft) for conditional human motion animation.
ImpDet: Exploring Implicit Fields for 3D Object Detection
Conventional 3D object detection approaches concentrate on bounding boxes representation learning with several parameters, i. e., localization, dimension, and orientation.
DST: Dynamic Substitute Training for Data-free Black-box Attack
With the wide applications of deep neural network models in various computer vision tasks, more and more works study the model vulnerability to adversarial examples.
Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images
We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses.
Density-preserving Deep Point Cloud Compression
To address this, we propose a novel deep point cloud compression method that preserves local density information.
Learning 6-DoF Object Poses to Grasp Category-level Objects by Language Instructions
This paper studies the task of any objects grasping from the known categories by free-form language instructions.
I Know What You Draw: Learning Grasp Detection Conditioned on a Few Freehand Sketches
The physical robot experiments confirm the utility of our method in object-cluttered scenes.
Cross-domain Federated Object Detection
Federated learning can enable multi-party collaborative learning without leaking client data.
RCLane: Relay Chain Prediction for Lane Detection
This is because most of the existing lane detection methods either treat the lane detection as a dense prediction or a detection task, few of them consider the unique topologies (Y-shape, Fork-shape, nearly horizontal lane) of the lane markers, which leads to sub-optimal solution.
Style Spectroscope: Improve Interpretability and Controllability through Fourier Analysis
We connect Fourier amplitude and phase with Gram matrices and a content reconstruction loss in style transfer, respectively.
AGO-Net: Association-Guided 3D Point Cloud Object Detection Network
A feasible method is investigated to construct conceptual scenes without external datasets.
Domain Discrepancy Aware Distillation for Model Aggregation in Federated Learning
In this paper, we first analyze the generalization bound of the aggregation model produced from knowledge distillation for the client domains, and then describe two challenges, server-to-client discrepancy and client-to-client discrepancy, brought to the aggregation model by the domain discrepancies.
Compositional Scene Modeling with Global Object-Centric Representations
Inspired by such an ability of humans, this paper proposes a compositional scene modeling method to infer global representations of canonical images of objects without any supervision.
Chinese Character Recognition with Radical-Structured Stroke Trees
In this paper, we represent each Chinese character as a stroke tree, which is organized according to its radical structures, to fully exploit the merits of both radical and stroke levels in a decent way.
Rethinking the Multi-view Stereo from the Perspective of Rendering-based Augmentation
To address these problems, we first apply one of the state-of-the-art learning-based MVS methods, --MVSFormer, to overcome intractable scenarios such as textureless and reflections regions suffered by traditional PatchMatch methods, but it fails in a few large scenes' reconstructions.
Weakly-Supervised Text Instance Segmentation
Text segmentation is a challenging vision task with many downstream applications.
Joint fMRI Decoding and Encoding with Latent Embedding Alignment
Our Latent Embedding Alignment (LEA) model concurrently recovers visual stimuli from fMRI signals and predicts brain activity from images within a unified framework.
Learning Versatile 3D Shape Generation with Improved AR Models
Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space.
Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model
Specifically, we first extract prototypes from the labeled data on the server and send them to the clients.
Collaborative Chinese Text Recognition with Personalized Federated Learning
In Chinese text recognition, to compensate for the insufficient local data and improve the performance of local few-shot character recognition, it is often necessary for one organization to collect a large amount of data from similar organizations.
OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning
The results demonstrate the shortcomings of state-of-the-art methods for learning meaningful representations from real-world data, despite their impressive performance on complex synthesis datasets.
Understanding Depth Map Progressively: Adaptive Distance Interval Separation for Monocular 3d Object Detection
In this paper, we propose a framework named the Adaptive Distance Interval Separation Network (ADISN) that adopts a novel perspective on understanding depth maps, as a form that lies between LiDAR and images.
Rethinking Person Re-identification from a Projection-on-Prototypes Perspective
In this paper, we rethink the role of the classifier in person Re-ID, and advocate a new perspective to conceive the classifier as a projection from image features to class prototypes.
Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification
Images with similar so-called fine-grained attributes (e. g., clothes and viewpoints) are encouraged to cluster together.
Ranked #2 on
Person Re-Identification
on PRCC
(mAP metric)
WALL-E: Embodied Robotic WAiter Load Lifting with Large Language Model
The target instruction is then forwarded to a visual grounding system for object pose and size estimation, following which the robot grasps the object accordingly.
DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions
Multiple object tracking (MOT) tends to become more challenging when severe occlusions occur.
Learning Versatile 3D Shape Generation with Improved Auto-regressive Models
Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space.
OpenAnnotate3D: Open-Vocabulary Auto-Labeling System for Multi-modal 3D Data
In the era of big data and large models, automatic annotating functions for multi-modal data are of great significance for real-world AI-driven applications, such as autonomous driving and embodied AI.
One-Shot Federated Learning with Classifier-Guided Diffusion Models
Leveraging the extensive knowledge stored in the pre-trained diffusion model, the synthetic datasets can assist us in surpassing the knowledge limitations of the client samples, resulting in aggregation models that even outperform the performance ceiling of centralized training in some cases, which is convincingly demonstrated in the sufficient quantification and visualization experiments conducted on three large-scale multi-domain image datasets.
Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection
Recent unsupervised anomaly detection methods often rely on feature extractors pretrained with auxiliary datasets or on well-crafted anomaly-simulated samples.
Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints
This ability is essential for humans to identify the same object while moving and to learn from vision efficiently.
Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection
In the odd-one-out task and two held-out configurations, RAISE can leverage acquired latent concepts and atomic rules to find the rule-breaking image in a matrix and handle problems with unseen combinations of rules and attributes.
Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability
In this paper, we extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective View
In autonomous driving, 3D occupancy prediction outputs voxel-wise status and semantic labels for more comprehensive understandings of 3D scenes compared with traditional perception tasks, such as 3D object detection and bird's-eye view (BEV) semantic segmentation.
