Search Results for author:
Found 327 papers, 140 papers with code
GhostNet: More Features from Cheap Operations
Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources.
Ranked #864 on
Image Classification
on ImageNet
Visformer: The Vision-friendly Transformer
The past year has witnessed the rapid development of applying the Transformer module to vision problems.
Ranked #507 on
Image Classification
on ImageNet
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Recently years have witnessed a rapid development of large language models (LLMs).
GhostNets on Heterogeneous Devices via Cheap Operations
The proposed C-Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks.
CenterNet: Keypoint Triplets for Object Detection
In object detection, keypoint-based approaches often suffer a large number of incorrect object bounding boxes, arguably due to the lack of an additional look into the cropped regions.
Ranked #105 on
Object Detection
on COCO test-dev
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design.
Ranked #16 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
Taking the perspective that horizontal detection is a special case for rotated object detection, in this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology, in terms of the relation between rotation and horizontal detection.
Ranked #14 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
The KFIoU Loss for Rotated Object Detection
This is in contrast to recent Gaussian modeling based rotation detectors e. g. GWD loss and KLD loss that involve a human-specified distribution distance metric which require additional hyperparameter tuning that vary across datasets and detectors.
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
Representing and rendering dynamic scenes has been an important but challenging task.
Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
In the past few years, convolutional neural networks (CNNs) have achieved milestones in medical image analysis.
Ranked #3 on
Medical Image Segmentation
on ACDC
Data-Free Learning of Student Networks
Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors.
AdderNet: Do We Really Need Multiplications in Deep Learning?
The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values.
Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast
In this paper, we present Pangu-Weather, a deep learning based system for fast and accurate global weather forecast.
Segment Anything in 3D with Radiance Fields
The Segment Anything Model (SAM) emerges as a powerful vision foundation model to generate high-quality 2D segmentation results.
ControlVideo: Training-free Controllable Text-to-Video Generation
Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temporal modeling.
GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting
Then we construct a Gaussian repair model based on diffusion models to supplement the omitted object information, where Gaussians are further refined.
CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
The style-based GAN (StyleGAN) architecture achieved state-of-the-art results for generating high-quality images, but it lacks explicit and precise control over camera poses.
Ranked #1 on
3D-Aware Image Synthesis
on FFHQ 256 x 256
Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
In this paper, we propose Attribute Mix, a data augmentation strategy at attribute level to expand the fine-grained samples.
Ranked #22 on
Fine-Grained Image Classification
on CUB-200-2011
GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
In recent times, the generation of 3D assets from text prompts has shown impressive results.
Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
RPP re-assigns these outliers to the parts they are closest to, resulting in refined parts with enhanced within-part consistency.
Ranked #3 on
Person Re-Identification
on UAV-Human
Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e. g., the complex scenes and lighting variations, viewpoint and pose changes, and the large number of identities in a camera network.
Ranked #11 on
Unsupervised Person Re-Identification
on DukeMTMC-reID
(Rank-10 metric)
Deep Modular Co-Attention Networks for Visual Question Answering
In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Attention (MCA) layers cascaded in depth.
Ranked #5 on
Question Answering
on SQA3D
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching for an optimal architecture.
Ranked #20 on
Neural Architecture Search
on CIFAR-10
Pixel Difference Networks for Efficient Edge Detection
A faster version of PiDiNet with less than 0. 1M parameters can still achieve comparable performance among state of the arts with 200 FPS.
Ranked #2 on
Edge Detection
on BRIND
Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
Recently, differentiable search methods have made major progress in reducing the computational costs of neural architecture search.
Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild
With the rapid development of neural architecture search (NAS), researchers found powerful network architectures for a wide range of vision tasks.
DocScanner: Robust Document Image Rectification with Progressive Learning
The iterative refinements make DocScanner converge to a robust and superior rectification performance, while the lightweight recurrent architecture ensures the running efficiency.
Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations
We find by theoretical analysis that the prediction discriminability and diversity could be separately measured by the Frobenius-norm and rank of the batch output matrix.
Gradually Vanishing Bridge for Adversarial Domain Adaptation
On the discriminator, GVB contributes to enhance the discriminating ability, and balance the adversarial training process.
Fast Dynamic Radiance Fields with Time-Aware Neural Voxels
A multi-distance interpolation method is proposed and applied on voxel features to model both small and large motions.
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
We validate AS-GCN in action recognition using two skeleton data sets, NTU-RGB+D and Kinetics.
Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation
Due to the domain discrepancy in visual domain adaptation, the performance of source model degrades when bumping into the high data density near decision boundary in target domain.
Co-Evolutionary Compression for Unpaired Image Translation
Generative adversarial networks (GANs) have been successfully used for considerable computer vision tasks, especially the image-to-image translation.
Cross-Scale Cost Aggregation for Stereo Matching
We firstly reformulate cost aggregation from a unified optimization perspective and show that different cost aggregation methods essentially differ in the choices of similarity kernels.
Multinomial Distribution Learning for Effective Neural Architecture Search
Therefore, NAS can be transformed to a multinomial distribution learning problem, i. e., the distribution is optimized to have a high expectation of the performance.
Corner Proposal Network for Anchor-free, Two-stage Object Detection
On the MS-COCO dataset, CPN achieves an AP of 49. 2% which is competitive among state-of-the-art object detection methods.
Ranked #83 on
Object Detection
on COCO test-dev
CenterNet++ for Object Detection
Our approach, named CenterNet, detects each object as a triplet keypoints (top-left and bottom-right corners and the center keypoint).
Ranked #35 on
Object Detection
on COCO test-dev
Rethinking Performance Estimation in Neural Architecture Search
In this paper, we provide a novel yet systematic rethinking of PE in a resource constrained regime, termed budgeted PE (BPE), which precisely and effectively estimates the performance of an architecture sampled from an architecture space.
Adversarial Domain Adaptation with Domain Mixup
In this paper, we present adversarial domain adaptation with domain mixup (DM-ADA), which guarantees domain-invariance in a more continuous latent space and guides the domain discriminator in judging samples' difference relative to source and target domains.
Location-Sensitive Visual Recognition with Cross-IOU Loss
Object detection, instance segmentation, and pose estimation are popular visual recognition tasks which require localizing the object by internal or boundary landmarks.
Ranked #45 on
Object Detection
on COCO test-dev
Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migration
iTPN is born with two elaborated designs: 1) The first pre-trained feature pyramid upon vision transformer (ViT).
A Fourier-based Framework for Domain Generalization
Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data.
Cross-domain Detection via Graph-induced Prototype Alignment
To mitigate these problems, we propose a Graph-induced Prototype Alignment (GPA) framework to seek for category-level domain alignment via elaborate prototype representations.
Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction
The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion feature learning.
TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
TS-CAM finally couples the patch tokens with the semantic-agnostic attention map to achieve semantic-aware localization.
Video Super-resolution with Temporal Group Attention
Video super-resolution, which aims at producing a high-resolution video from its corresponding low-resolution version, has recently drawn increasing attention.
Label Decoupling Framework for Salient Object Detection
Though remarkable progress has been achieved, we observe that the closer the pixel is to the edge, the more difficult it is to be predicted, because edge pixels have a very imbalance distribution.
Ranked #1 on
Saliency Detection
on HKU-IS
Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization
The fundamental difficulty in person re-identification (ReID) lies in learning the correspondence among individual cameras.
Ranked #16 on
Unsupervised Domain Adaptation
on Duke to Market
Direct Transfer Person Re-identification
Domain Adaptive Person Re-Identification
+2
CARS: Continuous Evolution for Efficient Neural Architecture Search
Architectures in the population that share parameters within one SuperNet in the latest generation will be tuned over the training dataset with a few epochs.
Rectifying the Shortcut Learning of Background for Few-Shot Learning
The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL).
Video Super-Resolution with Recurrent Structure-Detail Network
Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window.
CondenseNet V2: Sparse Feature Reactivation for Deep Networks
Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency.
MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
Transformers have offered a new methodology of designing neural networks for visual recognition.
Omni-GAN: On the Secrets of cGANs and Beyond
The conditional generative adversarial network (cGAN) is a powerful tool of generating high-quality images, but existing approaches mostly suffer unsatisfying performance or the risk of mode collapse.
Ranked #8 on
Conditional Image Generation
on ImageNet 128x128
UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
The main difficulty of person re-identification (ReID) lies in collecting annotated data and transferring the model across different domains.
Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters
Our approach bridges the gap from two aspects, namely, amending the estimation on the architectural gradients, and unifying the hyper-parameter settings in the search and re-training stages.
GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation
Subject to the huge semantic gap between natural and formal languages, neural semantic parsing is typically bottlenecked by its complexity of dealing with both input semantics and output syntax.
Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition
Inspired by the observation that humans learn to recognize the texts through both reading and writing, we propose to learn discrimination and generation by integrating contrastive learning and masked image modeling in our self-supervised method.
Masked Autoencoders are Robust Data Augmentors
Specifically, MRA consistently enhances the performance on supervised, semi-supervised as well as few-shot classification.
SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval
Moreover, in contrast to the general retrieval, the relevance in the legal domain is sensitive to key legal elements.
Filter Sketch for Network Pruning
Our approach, referred to as FilterSketch, encodes the second-order information of pre-trained weights, which enables the representation capacity of pruned networks to be recovered with a simple fine-tuning procedure.
HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling
A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e. g., ViT), albeit hierarchical vision transformers (e. g., Swin Transformer) have potentially better properties in formulating vision inputs.
SdAE: Self-distillated Masked Autoencoder
We also analyze how to build good views for the teacher branch to produce latent representation from the perspective of information bottleneck.
Bottom-Up Temporal Action Localization with Mutual Regularization
To alleviate this problem, we introduce two regularization terms to mutually regularize the learning procedure: the Intra-phase Consistency (IntraC) regularization is proposed to make the predictions verified inside each phase; and the Inter-phase Consistency (InterC) regularization is proposed to keep consistency between these phases.
Multi-Cue Correlation Filters for Robust Visual Tracking
By combining different types of features, our approach constructs multiple experts through Discriminative Correlation Filter (DCF) and each of them tracks the target independently.
Visual Recognition by Request
Humans have the ability of recognizing visual semantics in an unlimited granularity, but existing visual recognition algorithms cannot achieve this goal.
ChatterBox: Multi-round Multimodal Referring and Grounding
In this study, we establish a baseline for a new task named multimodal multi-round referring and grounding (MRG), opening up a promising direction for instance-level multimodal dialogues.
Adaptive Graph Representation Learning for Video Person Re-identification
While correlations between parts are ignored in the previous methods, to leverage the relations of different parts, we propose an innovative adaptive graph representation learning scheme for video person Re-ID, which enables the contextual interactions between relevant regional features.
Ranked #3 on
Person Re-Identification
on PRID2011
Graph Representation Learning
Video-Based Person Re-Identification
Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark
We also verified that models pre-trained on LaST can generalize well on existing datasets with short-term and cloth-changing scenarios.
Fine-Grained Semantically Aligned Vision-Language Pre-Training
Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks.
NeuSample: Neural Sample Field for Efficient View Synthesis
Neural radiance fields (NeRF) have shown great potentials in representing 3D scenes and synthesizing novel views, but the computational overhead of NeRF at the inference stage is still heavy.
Wavelet-Based Dual-Branch Network for Image Demoireing
When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality.
Federated Domain Generalization With Generalization Adjustment
Federated Domain Generalization (FedDG) attempts to learn a global model in a privacy-preserving manner that generalizes well to new clients possibly with domain shift.
Adversarial Training Towards Robust Multimedia Recommender System
To this end, we propose a novel solution named Adversarial Multimedia Recommendation (AMR), which can lead to a more robust multimedia recommender model by using adversarial learning.
Information Retrieval Multimedia
Bag of Instances Aggregation Boosts Self-supervised Distillation
Here bag of instances indicates a set of similar samples constructed by the teacher and are grouped within a bag, and the goal of distillation is to aggregate compact representations over the student with respect to instances in a bag.
A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems
As the focus on Large Language Models (LLMs) in the field of recommendation intensifies, the optimization of LLMs for recommendation purposes (referred to as LLM4Rec) assumes a crucial role in augmenting their effectiveness in providing recommendations.
Enhancing Person Re-identification in a Self-trained Subspace
To address this problem, in this paper, we propose a self-trained subspace learning paradigm for person re-ID which effectively utilizes both labeled and unlabeled data to learn a discriminative subspace where person images across disjoint camera views can be easily matched.
Partial Class Activation Attention for Semantic Segmentation
Current attention-based methods for semantic segmentation mainly model pixel relation through pairwise affinity and coarse segmentation.
Boosting Segment Anything Model Towards Open-Vocabulary Learning
The recent Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model, showcasing potent zero-shot generalization and flexible prompting.
HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks.
Deep Multimodal Neural Architecture Search
Most existing works focus on a single task and design neural architectures manually, which are highly task-specific and hard to generalize to different tasks.
Ranked #19 on
Visual Question Answering (VQA)
on VQA v2 test-std
Semantic-Aware Generation for Self-Supervised Visual Representation Learning
In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image based on the mid-level features.
Ranked #63 on
Semantic Segmentation
on Cityscapes test
Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction
To address the first issue, we propose adaptive graph scattering, which leverages multiple trainable band-pass graph filters to decompose pose features into richer graph spectrum bands.
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
Towards this goal, we propose a framework with a unified view of PETL called visual-PETL (V-PETL) to investigate the effects of different PETL techniques, data scales of downstream domains, positions of trainable parameters, and other aspects affecting the trade-off.
CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
In contrast to great success of memory-consuming face editing methods at a low resolution, to manipulate high-resolution (HR) facial images, i. e., typically larger than 7682 pixels, with very limited memory is still challenging.
Greedy Gradient Ensemble for Robust Visual Question Answering
Language bias is a critical issue in Visual Question Answering (VQA), where models often exploit dataset biases for the final decision without considering the image information.
Ranked #2 on
Visual Question Answering (VQA)
on VQA-CP
Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers
The past year has witnessed a rapid development of masked image modeling (MIM).
Hadamard Matrix Guided Online Hashing
We then treat the learning of hash functions as a set of binary classification problems to fit the assigned target code.
Single Camera Training for Person Re-identification
Differently, this paper investigates ReID in an unexplored single-camera-training (SCT) setting, where each person in the training set appears in only one camera.
TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge
Real-time semantic video segmentation is a challenging task due to the strict requirements of inference speed.
GOLD-NAS: Gradual, One-Level, Differentiable
There has been a large literature of neural architecture search, but most existing work made use of heuristic rules that largely constrained the search flexibility.
Semantic-guided Pixel Sampling for Cloth-Changing Person Re-identification
The key to this task is to exploit cloth-irrelevant cues.
DE-Net: Dynamic Text-guided Image Editing Adversarial Networks
To solve these limitations, we propose: (i) a Dynamic Editing Block (DEBlock) which composes different editing modules dynamically for various editing requirements.
Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding
Visual grounding aims to localize an object in an image referred to by a textual query phrase.
Ranked #9 on
Phrase Grounding
on Flickr30k Entities Test
Towards Visual Feature Translation
In this paper, we make the first attempt towards visual feature translation to break through the barrier of using features across different visual search systems.
Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning
We consider spatial contexts, for which we solve so-called jigsaw puzzles, i. e., each image is cut into grids and then disordered, and the goal is to recover the correct configuration.
Towards 3D Molecule-Text Interpretation in Language Models
Through 3D molecule-text alignment and 3D molecule-centric instruction tuning, 3D-MoLM establishes an integration of 3D molecular encoder and LM.
Wnet: Audio-Guided Video Object Segmentation via Wavelet-Based Cross-Modal Denoising Networks
Audio-Guided video semantic segmentation is a challenging problem in visual analysis and editing, which automatically separates foreground objects from background in a video sequence according to the referring audio expressions.
AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations
This ensures the resultant TERs of individual images contain the {\em intrinsic} information about their visual structures that would equivary {\em extricably} under various transformations in a generalized {\em nonlinear} case.
Self-Adaptively Learning to Demoire from Focused and Defocused Image Pairs
In this paper, we propose a self-adaptive learning method for demoireing a high-frequency image, with the help of an additional defocused moire-free blur image.
Information Competing Process for Learning Diversified Representations
Learning representations with diversified information remains as an open problem.
Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing
In recent years, cross-modal hashing (CMH) has attracted increasing attentions, mainly because its potential ability of mapping contents from different modalities, especially in vision and language, into the same space, so that it becomes efficient in cross-modal data retrieval.
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
DATA: Domain-Aware and Task-Aware Self-supervised Learning
However, due to the high training costs and the unconsciousness of downstream usages, most self-supervised learning methods lack the capability to correspond to the diversities of downstream scenarios, as there are various data domains, different vision tasks and latency constraints on models.
Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation
Based on the STA score, we are able to progressively prune the tokens without introducing any additional parameters or requiring further re-training.
Self-Regulated Learning for Egocentric Video Activity Anticipation
Future activity anticipation is a challenging problem in egocentric vision.
DeeCap: Dynamic Early Exiting for Efficient Image Captioning
On one hand, the representation in shallow layers lacks high-level semantic and sufficient cross-modal fusion information for accurate prediction.
Projection & Probability-Driven Black-Box Attack
For reducing the solution space, we first model the adversarial perturbation optimization problem as a process of recovering frequency-sparse perturbations with compressed sensing, under the setting that random noise in the low-frequency space is more likely to be adversarial.
Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio
Automatic designing computationally efficient neural networks has received much attention in recent years.
DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing
Accordingly, DR$^{2}$-Net consists of two components, \emph{i. e.,} linear mapping network and residual network, respectively.
Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training
During inference, instead of changing the motion generator, our method reformulates the input text into a masked motion as the prompt for the motion generator to ``reconstruct'' the motion.
Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization
In our approach, we first collect tracklet data within each camera by automatic person detection and tracking.
Towards Compact CNNs via Collaborative Compression
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression.
A Real-time Global Inference Network for One-stage Referring Expression Comprehension
Referring Expression Comprehension (REC) is an emerging research spot in computer vision, which refers to detecting the target region in an image given an text description.
Circumventing Outliers of AutoAugment with Knowledge Distillation
AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper setting may degenerate network optimization.
Ranked #185 on
Image Classification
on ImageNet
Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks
To learn the sampling policy, a Markov decision process is embedded into the search algorithm and a moving average is applied for better stability.
When Parameter-efficient Tuning Meets General-purpose Vision-language Models
Instruction tuning has shown promising potential for developing general-purpose AI capabilities by using large-scale pre-trained models and boosts growing research to integrate multimodal information for creative applications.
Harmonized Multimodal Learning with Gaussian Process Latent Variable Models
Multimodal learning aims to discover the relationship between multiple modalities.
General Greedy De-bias Learning
Existing de-bias learning frameworks try to capture specific dataset bias by annotations but they fail to handle complicated OOD scenarios.
Active Pointly-Supervised Instance Segmentation
In this paper, we present an economic active learning setting, named active pointly-supervised instance segmentation (APIS), which starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object.
AiluRus: A Scalable ViT Framework for Dense Prediction
Specifically, at the intermediate layer of the ViT, we utilize a spatial-aware density-based clustering algorithm to select representative tokens from the token sequence.
LogFormer: A Pre-train and Tuning Pipeline for Log Anomaly Detection
Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps).
FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation
However, in addition to previous explorations for improvement in federated averaging, our analysis shows that another critical bottleneck is the poorer optima of client models in more heterogeneous conditions.
Learning Transferable Pedestrian Representation from Multimodal Information Supervision
Recent researches on unsupervised person re-identification~(reID) have demonstrated that pre-training on unlabeled person images achieves superior performance on downstream reID tasks than pre-training on ImageNet.
One-bit Supervision for Image Classification
Instead of training a model upon the accurate label of each sample, our setting requires the model to query with a predicted label of each sample and learn from the answer whether the guess is correct.
Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos
In this paper, we introduce a new task, named Temporal Emotion Localization in videos~(TEL), which aims to detect human emotions and localize their corresponding temporal boundaries in untrimmed videos with aligned subtitles.
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications.
Unsupervised Person Re-identification via Softened Similarity Learning
Person re-identification (re-ID) is an important topic in computer vision.
Fast Non-Local Neural Networks with Spectral Residual Learning
We show its equivalence to conducting residual learning in some spectral domain and carefully re-formulate a variety of neural layers into their spectral forms, such as ReLU or convolutions.
DisturbLabel: Regularizing CNN on the Loss Layer
During a long period of time we are combating over-fitting in the CNN training process with model regularization, including weight decay, model averaging, data augmentation, etc.
Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition
To mitigate the computational and storage demands, recent research has explored Parameter-Efficient Fine-Tuning (PEFT), which focuses on tuning a minimal number of parameters for efficient adaptation.
Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions
During reasoning, for leaf nodes, LLMs choose a more confident answer from Closed-book QA that employs parametric knowledge and Open-book QA that employs retrieved external knowledge, thus eliminating the negative retrieval problem.
Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View
Concretely, we design a novel interpretation scheme whereby the loss of mis-predicted frequent and sparse answers of the same question type is distinctly exhibited during the late training phase.
Latency-Aware Differentiable Neural Architecture Search
However, these methods suffer the difficulty in optimizing network, so that the searched network is often unfriendly to hardware.
Semi-Autoregressive Image Captioning
Non-autoregressive image captioning with continuous iterative refinement, which eliminates the sequential dependence in a sentence generation, can achieve comparable performance to the autoregressive counterparts with a considerable acceleration.
See Blue Sky: Deep Image Dehaze Using Paired and Unpaired Training Images
The issue of image haze removal has attracted wide attention in recent years.
Prototype-guided Cross-task Knowledge Distillation for Large-scale Models
Considering the complexity and variability of real scene tasks, we propose a Prototype-guided Cross-task Knowledge Distillation (ProC-KD) approach to transfer the intrinsic local-level object knowledge of a large-scale teacher network to various task scenarios.
SIFT Meets CNN: A Decade Survey of Instance Retrieval
This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods.
API-Net: Robust Generative Classifier via a Single Discriminator
On the contrary, a discriminative classifier only models the conditional distribution of labels given inputs, but benefits from effective optimization owing to its succinct structure.
Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
Second, most previous weakly supervised REG methods ignore the discriminative location and context of the referent, causing difficulties in distinguishing the target from other same-category objects.
Zigzag Learning for Weakly Supervised Object Detection
Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds.
Social Anchor-Unit Graph Regularized Tensor Completion for Large-Scale Image Retagging
Recent approaches simultaneously explore visual, user and tag information to improve the performance of image retagging by constructing and exploring an image-tag-user graph.
A Novel Multi-Task Tensor Correlation Neural Network for Facial Attribute Prediction
In this paper, we propose a novel multi-attribute tensor correlation neural network (MTCN) for face attribute prediction.
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
Selected from 10 hours raw videos, about 80, 000 representative frames are fully annotated with bounding boxes as well as up to 14 kinds of attributes (e. g., weather condition, flying altitude, camera view, vehicle category, and occlusion) for three fundamental computer vision tasks: object detection, single object tracking, and multiple object tracking.
Ranked #5 on
Object Detection
on UAVDT
LVreID: Person Re-Identification with Long Sequence Videos
This paper mainly establishes a large-scale Long sequence Video database for person re-IDentification (LVreID).
Pseudo-positive regularization for deep person re-identification
A small proportion of these retrieved samples are randomly selected as the Pseudo Positive samples and added to the target training set for the supervised CNN training.
Deep Representation Learning with Part Loss for Person Re-Identification
The representation learning risk is evaluated by the proposed part loss, which automatically generates several parts for an image, and computes the person classification loss on each part separately.
Ranked #97 on
Person Re-Identification
on Market-1501
Learning to Learn Image Classifiers with Visual Analogy
We then propose an out-of-sample embedding method to learn the embedding of a new class represented by a few samples through its visual analogy with base classes and derive the classification parameters for the new class.
Effective Image Retrieval via Multilinear Multi-index Fusion
In this paper, we propose a new multi-index fusion scheme for image retrieval.
Pose-driven Deep Convolutional Model for Person Re-identification
Our deep architecture explicitly leverages the human part cues to alleviate the pose variations and learn robust feature representations from both the global image and different local parts.
Ranked #105 on
Person Re-Identification
on Market-1501
E$^2$BoWs: An End-to-End Bag-of-Words Model via Deep Convolutional Neural Network
To conquer these issues, we propose an End-to-End BoWs (E$^2$BoWs) model based on Deep Convolutional Neural Network (DCNN).
GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
Targeting to solve these problems, this work proposes a Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework, respectively.
Ranked #93 on
Person Re-Identification
on Market-1501
Multidimensional Scaling on Multiple Input Distance Matrices
How to do multidimensional scaling on multiple input distance matrices is still unsolved to our best knowledge.
One-Shot Fine-Grained Instance Retrieval
Aiming to conquer this issue, we propose a retrieval task named One-Shot Fine-Grained Instance Retrieval (OSFGIR).
Ensemble of Part Detectors for Simultaneous Classification and Localization
Part-based representation has been proven to be effective for a variety of visual applications.
Part-based Deep Hashing for Large-scale Person Re-identification
In the experiment, we show that the proposed Part-based Deep Hashing method yields very competitive re-id accuracy on the large-scale Market-1501 and Market-1501+500K datasets.
Person Re-identification in the Wild
Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification accuracy and assessing the effectiveness of different detectors for re-identification.
Scalable Person Re-identification on Supervised Smoothed Manifold
Most existing person re-identification algorithms either extract robust visual features or learn discriminative metrics for person images.
Ranked #100 on
Person Re-Identification
on Market-1501
Deep Attributes Driven Multi-Camera Person Re-identification
And we propose a semi-supervised attribute learning framework which progressively boosts the accuracy of attributes only using a limited number of labeled data.
Geometric Neural Phrase Pooling: Modeling the Spatial Co-occurrence of Neurons
For this, we consider the neurons in the hidden layer as neural words, and construct a set of geometric neural phrases on top of them.
Coarse2Fine: Two-Layer Fusion For Image Retrieval
Departing from the previous methods fusing multiple image descriptors simultaneously, C2F is featured by a layered procedure composed by filtering and refining.
InterActive: Inter-Layer Activeness Propagation
An increasing number of computer vision tasks can be tackled with deep features, which are the intermediate outputs of a pre-trained Convolutional Neural Network.
Good Practice in CNN Feature Transfer
The objective of this paper is the effective transfer of the Convolutional Neural Network (CNN) feature in image search and classification.
Geometric Hypergraph Learning for Visual Tracking
Graph based representation is widely used in visual tracking field by finding correct correspondences between target parts in consecutive frames.
Person Re-identification Meets Image Search
In the light of recent advances in image search, this paper proposes to treat person re-identification as an image search problem.
Visual Reranking with Improved Image Graph
This paper introduces an improved reranking method for the Bag-of-Words (BoW) based image search.
Seeing the Big Picture: Deep Embedding with Contextual Evidences
Specifically, the Convolutional Neural Network (CNN) is employed to extract features from regional and global patches, leading to the so-called "Deep Embedding" framework.
Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval
Albeit simple, Bayes merging can be well applied in various merging tasks, and consistently improves the baselines on multi-vocabulary merging.
Packing and Padding: Coupled Multi-index for Accurate Image Retrieval
Specifically, we exploit the fusion of local color feature into c-MI.
Super-pixel cloud detection using Hierarchical Fusion CNN
Secondly, super-pixel level database is used to train our cloud detection models based on CNN and deep forest.
Generalized Coarse-to-Fine Visual Recognition with Progressive Training
Computer vision is difficult, partly because the desired mathematical function connecting input and output data is often complex, fuzzy and thus hard to learn.
Phase Collaborative Network for Two-Phase Medical Image Segmentation
However, in medical image analysis, fusing prediction from two phases is often difficult, because (i) there is a domain gap between two phases, and (ii) the semantic labels are not pixel-wise corresponded even for images scanned from the same patient.
Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption
Unsupervised domain adaption aims to learn a powerful classifier for the target domain given a labeled source data set and an unlabeled target data set.
Universal Perturbation Attack Against Image Retrieval
In this paper, we make the first attempt in attacking image retrieval systems.
Accelerate CNN via Recursive Bayesian Pruning
A new dropout-based measurement of redundancy, which facilitate the computation of posterior assuming inter-layer dependency, is introduced.
Super-Bit Locality-Sensitive Hashing
Sign-random-projection locality-sensitive hashing (SRP-LSH) is a probabilistic dimension reduction method which provides an unbiased estimate of angular similarity, yet suffers from the large variance of its estimation.
Deep Hashing via Discrepancy Minimization
This paper presents a discrepancy minimizing model to address the discrete optimization problem in hashing learning.
Collaborative Deep Reinforcement Learning for Multi-Object Tracking
To address this, we develop a deep prediction-decision network in our C-DRL, which simultaneously detects and predicts objects under a unified network via deep reinforcement learning.
Binary Code Ranking with Weighted Hamming Distance
In this paper, we propose a weighted Hamming distance ranking algorithm (WhRank) to rank the binary codes of hashing methods.
Lp-Norm IDF for Large Scale Image Search
Further, by counting for the term-frequency in each image, the proposed L p -norm IDF helps to alleviate the visual word burstiness phenomenon.
Orientational Pyramid Matching for Recognizing Indoor Scenes
The novelty lies in that OPM uses the 3D orientations to form the pyramid and produce the pooling regions, which is unlike SPM that uses the spatial positions to form the pyramid.
Semi-supervised Relational Topic Model for Weakly Annotated Image Recognition in Social Media
In such way, we can efficiently leverage the loosely related tags, and build an intermediate level representation for a collection of weakly annotated images.
Query-Adaptive Late Fusion for Image Search and Person Re-Identification
However, in a more realistic situation, one does not know in advance whether a feature is effective or not for a given query.
Interaction Part Mining: A Mid-Level Approach for Fine-Grained Action Recognition
Secondly, these object regions are matched and tracked across frames to form a large spatio-temporal graph based on the appearance matching and the dense motion trajectories through them.
Fine-grained Action Recognition
Human-Object Interaction Detection
+2
Picking Deep Filter Responses for Fine-Grained Image Recognition
Recognizing fine-grained sub-categories such as birds and dogs is extremely challenging due to the highly localized and subtle differences in some specific parts.
Cascaded Interactional Targeting Network for Egocentric Video Analysis
Firstly, a novel EM-like learning framework is proposed to train the pixel-level deep convolutional neural network (DCNN) by seamlessly integrating weakly supervised data (i. e., massive bounding box annotations) with a small set of strongly supervised data (i. e., fully annotated hand segmentation maps) to achieve state-of-the-art hand segmentation performance.
Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Description
This paper contributes to: 1)The first in-depth study of the weakness inherent in data-driven static fusion methods for video captioning.
RIDE: Reversal Invariant Descriptor Enhancement
In many fine-grained object recognition datasets, image orientation (left/right) might vary from sample to sample.
Scalable Person Re-Identification: A Benchmark
As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor.
Ranked #90 on
Person Re-Identification
on DukeMTMC-reID
Multi-Task Learning With Low Rank Attribute Embedding for Person Re-Identification
Since attributes are generally correlated, we introduce a low rank attribute embedding into the MTL formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered to better describe people.
Similarity Gaussian Process Latent Variable Model for Multi-Modal Data Analysis
Data from real applications involve multiple modalities representing content with the same semantics and deliver rich information from complementary aspects.
Ensemble Diffusion for Retrieval
This stimulates a great research interest of considering similarity fusion in the framework of diffusion process (i. e., fusion with diffusion) for robust retrieval.
Multimodal Gaussian Process Latent Variable Models With Harmonization
We incorporate the harmonization mechanism into the learning process of multimodal GPLVMs.
Adversarial Attack and Defense on Point Sets
A set of novel 3D point cloud attack operations are proposed via pointwise gradient perturbation and adversarial point attachment / detachment.
Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling
Thereby, we for the first time propose an end-to-end learnable and task-agnostic sampling operation, named Gumbel Subset Sampling (GSS), to select a representative subset of input points.
BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation
Existing methods for age estimation usually apply a divide-and-conquer strategy to deal with heterogeneous data caused by the non-stationary aging process.
Ranked #2 on
Age Estimation
on FGNET
Data Priming Network for Automatic Check-Out
In this paper, we propose a new data priming method to solve the domain adaptation problem.
Deep Fitting Degree Scoring Network for Monocular 3D Object Detection
In this paper, we propose to learn a deep fitting degree scoring network for monocular 3D object detection, which aims to score fitting degree between proposals and object conclusively.
Ranked #7 on
Vehicle Pose Estimation
on KITTI Cars Hard
Handwritten Chinese Font Generation with Collaborative Stroke Refinement
Automatic character generation is an appealing solution for new typeface design, especially for Chinese typefaces including over 3700 most commonly-used characters.
Efficient Discrete Supervised Hashing for Large-scale Cross-modal Retrieval
In this paper, to address above issues, we propose a supervised cross-modal hashing method based on matrix factorization dubbed Efficient Discrete Supervised Hashing (EDSH).
