Search Results for author:
Found 52 papers, 35 papers with code
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.
ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing
We also evaluate some robust models including both adversarially trained models and other robust trained models and find that some models show worse robustness against attribute changes than vanilla models.
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.
F3Net: Fusion, Feedback and Focus for Salient Object Detection
Furthermore, different from binary cross entropy, the proposed PPA loss doesn't treat pixels equally, which can synthesize the local structure information of a pixel to guide the network to focus more on local details.
Ranked #5 on
Salient Object Detection
on DUT-OMRON
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
Parsing-based View-aware Embedding Network for Vehicle Re-Identification
Vehicle Re-Identification is to find images of the same vehicle from various views in the cross-camera scenario.
Attribute Group Editing for Reliable Few-shot Image Generation
Few-shot image generation is a challenging task even using the state-of-the-art Generative Adversarial Networks (GANs).
Heuristic Domain Adaptation
In visual domain adaptation (DA), separating the domain-specific characteristics from the domain-invariant representations is an ill-posed problem.
Hierarchical Modular Network for Video Captioning
(II) Predicate level, which learns the actions conditioned on highlighted objects and is supervised by the predicate in captions.
Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
We address the unsupervised open domain recognition (UODR) problem, where categories in labeled source domain S is only a subset of those in unlabeled target domain T. The task is to correctly classify all samples in T including known and unknown categories.
Learning fragment self-attention embeddings for image-text matching
In this paper, we propose Self-Attention Embeddings (SAEM) to exploit fragment relations in images or texts by self-attention mechanism, and aggregate fragment information into visual and textual embeddings.
Mining Latent Structures for Multimedia Recommendation
To be specific, in the proposed LATTICE model, we devise a novel modality-aware structure learning layer, which learns item-item structures for each modality and aggregates multiple modalities to obtain latent item graphs.
Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
It builds the correspondence between image region proposal and query in an adaptive manner: adaptive grounding and collaborative reconstruction.
Composite Adversarial Attacks
Adversarial attack is a technique for deceiving Machine Learning (ML) models, which provides a way to evaluate the adversarial robustness.
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
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.
Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer
Semi-supervised domain adaptation (SSDA) aims to solve tasks in target domain by utilizing transferable information learned from the available source domain and a few labeled target data.
A Graph Regularized Deep Neural Network for Unsupervised Image Representation Learning
Deep Auto-Encoder (DAE) has shown its promising power in high-level representation learning.
The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation
Existing methods suffer from the trade-off between the quality and diversity of generated images.
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.
Orthogonal Temporal Interpolation for Zero-Shot Video Recognition
We propose a model called OTI for ZSVR by employing orthogonal temporal interpolation and the matching loss based on VLMs.
Ranked #1 on
Zero-Shot Action Recognition
on UCF101
Modeling Temporal Concept Receptive Field Dynamically for Untrimmed Video Analysis
Based on TDC, we propose the temporal dynamic concept modeling network (TDCMN) to learn an accurate and complete concept representation for efficient untrimmed video analysis.
Multi-Attention Network for Compressed Video Referring Object Segmentation
To address this problem, we propose a multi-attention network which consists of dual-path dual-attention module and a query-based cross-modal Transformer module.
Ranked #5 on
Referring Expression Segmentation
on A2D Sentences
Knowledge-guided Pairwise Reconstruction Network for Weakly Supervised Referring Expression Grounding
Weakly supervised referring expression grounding (REG) aims at localizing the referential entity in an image according to linguistic query, where the mapping between the image region (proposal) and the query is unknown in the training stage.
Stable Attribute Group Editing for Reliable Few-shot Image Generation
SAGE takes use of all given few-shot images and estimates a class center embedding based on the category-relevant attribute dictionary.
State-Relabeling Adversarial Active Learning
In this paper, we propose a state relabeling adversarial active learning model (SRAAL), that leverages both the annotation and the labeled/unlabeled state information for deriving the most informative unlabeled samples.
Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video
Temporal Sentence Grounding in Video (TSGV) is troubled by dataset bias issue, which is caused by the uneven temporal distribution of the target moments for samples with similar semantic components in input videos or query texts.
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.
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.
Open-Set Knowledge-Based Visual Question Answering with Inference Paths
Given an image and an associated textual question, the purpose of Knowledge-Based Visual Question Answering (KB-VQA) is to provide a correct answer to the question with the aid of external knowledge bases.
Less Is More: Picking Informative Frames for Video Captioning
We propose a plug-and-play PickNet to perform informative frame picking in video captioning.
Multi-level Discriminative Dictionary Learning towards Hierarchical Visual Categorization
For each internode of the hierarchical category structure, a discriminative dictionary and a set of classification models are learnt for visual categorization, and the dictionaries in different layers are learnt to exploit the discriminative visual properties of different granularity.
Online Asymmetric Similarity Learning for Cross-Modal Retrieval
In this paper, we propose an online learning method to learn the similarity function between heterogeneous modalities by preserving the relative similarity in the training data, which is modeled as a set of bi-directional hinge loss constraints on the cross-modal training triplets.
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.
Multimodal Gaussian Process Latent Variable Models With Harmonization
We incorporate the harmonization mechanism into the learning process of multimodal GPLVMs.
Sharp Multiple Instance Learning for DeepFake Video Detection
A sharp MIL (S-MIL) is proposed which builds direct mapping from instance embeddings to bag prediction, rather than from instance embeddings to instance prediction and then to bag prediction in traditional MIL.
Interpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision
In this paper, we rethink implicit reasoning process in VQA, and propose a new formulation which maximizes the log-likelihood of joint distribution for the observed question and predicted answer.
Semantic Editing On Segmentation Map Via Multi-Expansion Loss
Each MEx area has the mask area of the generation as the majority and the boundary of original context as the minority.
QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval
Comprehensive experiments show that the proposed attack achieves a high attack success rate with few queries against the image retrieval systems under the black-box setting.
DVCFlow: Modeling Information Flow Towards Human-like Video Captioning
Dense video captioning (DVC) aims to generate multi-sentence descriptions to elucidate the multiple events in the video, which is challenging and demands visual consistency, discoursal coherence, and linguistic diversity.
IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning
Conditional image generation is an active research topic including text2image and image translation.
Conditional Image Generation
Generative Adversarial Network
+1
Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency
Furthermore, we devise the spatio-temporal correlative map as a style-independent, global-aware regularization on the perceptual motion consistency.
Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks
Deep neural networks (DNN) are a promising tool in medical applications.
Multimodal Brain Disease Classification with Functional Interaction Learning from Single fMRI Volume
The low representation ability of FC leads to poor performance in clinical practice, especially when dealing with multimodal medical data involving multiple types of visual signals and textual records for brain diseases.
Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection
Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels.
Dual-view Curricular Optimal Transport for Cross-lingual Cross-modal Retrieval
Therefore, we propose Dual-view Curricular Optimal Transport (DCOT) to learn with noisy correspondence in CCR.
R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation
Recent text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images given text-prompts as input.
A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes
Three-Dimensional (3D) dense captioning is an emerging vision-language bridging task that aims to generate multiple detailed and accurate descriptions for 3D scenes.
Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments
In this paper, we address unsupervised domain adaptation under noisy environments, which is more challenging and practical than traditional domain adaptation.
