Search Results for author:
Found 96 papers, 50 papers with code
Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction
This implies the great potential of the semantic correlations for the entity-independent inductive link prediction task.
T2IW: Joint Text to Image & Watermark Generation
Furthermore, we strengthen the watermark robustness of our approach by subjecting the compound image to various post-processing attacks, with minimal pixel distortion observed in the revealed watermark.
A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design
In particular, we notice that the runtime of the Resub and Mfs2 operators often dominates the overall runtime of LS optimization processes.
Balanced Classification: A Unified Framework for Long-Tailed Object Detection
In this paper, we contend that the learning bias originates from two factors: 1) the unequal competition arising from the imbalanced distribution of foreground categories, and 2) the lack of sample diversity in tail categories.
Ranked #1 on
Long-tailed Object Detection
on LVIS v1.0 val
MomentDiff: Generative Video Moment Retrieval from Random to Real
Video moment retrieval pursues an efficient and generalized solution to identify the specific temporal segments within an untrimmed video that correspond to a given language description.
DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation
While large-scale pre-trained text-to-image models can synthesize diverse and high-quality human-centric images, an intractable problem is how to preserve the face identity for conditioned face images.
Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization
Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training.
Multiple Instance Learning
Weakly Supervised Action Localization
+2
ExpertPrompting: Instructing Large Language Models to be Distinguished Experts
The answering quality of an aligned large language model (LLM) can be drastically improved if treated with proper crafting of prompts.
Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation
Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook.
Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization
Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook.
Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition
Vision model have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task.
Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendation
However, such a manner inevitably learns unstable feature interactions, i. e., the ones that exhibit strong correlations in historical data but generalize poorly for future serving.
$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
In-Context Learning (ICL), which formulates target tasks as prompt completion conditioned on in-context demonstrations, has become the prevailing utilization of LLMs.
Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution
The appealing features of RSD-OA include that: (1) RSD-OA is invariant to visual distractions, as it is conditioned on the predefined subsequent action sequence without task-irrelevant information from transition dynamics, and (2) the reward sequence captures long-term task-relevant information in both rewards and transition dynamics.
De Novo Molecular Generation via Connection-aware Motif Mining
The obtained motif vocabulary consists of not only molecular motifs (i. e., the frequent fragments), but also their connection information, indicating how the motifs are connected with each other.
Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model
Cut selection -- which aims to select a proper subset of the candidate cuts to improve the efficiency of solving MILPs -- heavily depends on (P1) which cuts should be preferred, and (P2) how many cuts should be selected.
Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation
POP builds a set of orthogonal prototypes, each of which represents a semantic class, and makes the prediction for each class separately based on the features projected onto its prototype.
Crossing the Gap: Domain Generalization for Image Captioning
In this paper, we introduce a new setting called Domain Generalization for Image Captioning (DGIC), where the data from the target domain is unseen in the learning process.
Learning Semantic Relationship Among Instances for Image-Text Matching
Image-text matching, a bridge connecting image and language, is an important task, which generally learns a holistic cross-modal embedding to achieve a high-quality semantic alignment between the two modalities.
Dynamic Generative Targeted Attacks With Pattern Injection
Concretely, the former adopts a dynamic convolution kernel and a static convolution kernel for the specific instance and the global dataset, respectively, which can inherit the advantages of both instance-specific and instance-agnostic attacks.
Exploring Stroke-Level Modifications for Scene Text Editing
Moreover, two new datasets (Tamper-Syn2k and Tamper-Scene) are proposed to fill the blank of public evaluation datasets.
Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning
They have overlooked the wide characteristic changes of different classes and can not model abundant intra-class variations for generations.
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting
In this paper, we argue that the limited capacity of language models comes from 1) implicit language modeling; 2) unidirectional feature representation; and 3) language model with noise input.
Ranked #3 on
Text Spotting
on SCUT-CTW1500
Cross-Modality Transformer for Visible-Infrared Person Re-Identification
To alleviate the above issues, we propose a novel Cross-Modality Transformer (CMT) to jointly explore a modality-level alignment module and an instance-level module for VI-ReID.
Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity
In this paper, we consider introducing an auxiliary task of Chinese pronunciation prediction (CPP) to improve CSC, and, for the first time, systematically discuss the adaptivity and granularity of this auxiliary task.
Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets
On channel aspect, we introduce a dynamic feature aggregation module in MLP and a brand new "head token" design in multi-head self-attention module to help re-calibrate channel representation and make different channel group representation interacts with each other.
DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation
Text-to-image generation aims at generating realistic images which are semantically consistent with the given text.
MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition
In DestFormer, the spatial and temporal dimensions of the 4D point cloud videos are decoupled to achieve efficient self-attention for learning both long-term and short-term features.
REMOT: A Region-to-Whole Framework for Realistic Human Motion Transfer
Human Video Motion Transfer (HVMT) aims to, given an image of a source person, generate his/her video that imitates the motion of the driving person.
MFAN: Multi-modal Feature-enhanced Attention Networks for Rumor Detection
Rumor spreaders are increasingly taking advantage of multimedia content to attract and mislead news consumers on social media.
Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network
On the one hand, their performance will dramatically degrade along with the increasing sparsity of KGs.
Addressing Confounding Feature Issue for Causal Recommendation
We demonstrate DCR on the backbone model of neural factorization machine (NFM), showing that DCR leads to more accurate prediction of user preference with small inference time cost.
Rumor Detection with Self-supervised Learning on Texts and Social Graph
At the core is to model the rumor characteristics inherent in rich information, such as propagation patterns in social network and semantic patterns in post content, and differentiate them from the truth.
Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework
Therefore, researchers start to focus on a new task, Part-level Action Parsing (PAP), which aims to not only predict the video-level action but also recognize the frame-level fine-grained actions or interactions of body parts for each person in the video.
Motion-Modulated Temporal Fragment Alignment Network for Few-Shot Action Recognition
To address this issue, we propose an end-to-end Motion-modulated Temporal Fragment Alignment Network (MTFAN) by jointly exploring the task-specific motion modulation and the multi-level temporal fragment alignment for Few-Shot Action Recognition (FSAR).
Negative-Aware Attention Framework for Image-Text Matching
Image-text matching, as a fundamental task, bridges the gap between vision and language.
Partial Class Activation Attention for Semantic Segmentation
Current attention-based methods for semantic segmentation mainly model pixel relation through pairwise affinity and coarse segmentation.
From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
Such operation guides the vision model to use not only the visual texture of characters, but also the linguistic information in visual context for recognition when the visual cues are confused (e. g. occlusion, noise, etc.).
Causal Incremental Graph Convolution for Recommender System Retraining
Towards the goal, we propose a \textit{Causal Incremental Graph Convolution} approach, which consists of two new operators named \textit{Incremental Graph Convolution} (IGC) and \textit{Colliding Effect Distillation} (CED) to estimate the output of full graph convolution.
PERT: A Progressively Region-based Network for Scene Text Removal
However, there exists two problems: 1) the implicit erasure guidance causes the excessive erasure to non-text areas; 2) the one-stage erasure lacks the exhaustive removal of text region.
Lesion-Aware Transformers for Diabetic Retinopathy Grading
First, to the best of our knowledge, this is the first work to formulate lesion discovery as a weakly supervised lesion localization problem via a transformer decoder.
Uncertainty Guided Collaborative Training for Weakly Supervised Temporal Action Detection
To alleviate this problem, we propose a novel Uncertainty Guided Collaborative Training (UGCT) strategy, which mainly includes two key designs: (1) The first design is an online pseudo label generation module, in which the RGB and FLOW streams work collaboratively to learn from each other.
Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning
Cross-modal correlation provides an inherent supervision for video unsupervised representation learning.
Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer
To address these issues, we propose a novel end-to-end Part-Aware Transformer (PAT) for occluded person Re-ID through diverse part discovery via a transformer encoderdecoder architecture, including a pixel context based transformer encoder and a part prototype based transformer decoder.
Causal Intervention for Leveraging Popularity Bias in Recommendation
This work studies an unexplored problem in recommendation -- how to leverage popularity bias to improve the recommendation accuracy.
Action Unit Memory Network for Weakly Supervised Temporal Action Localization
In this paper, we present an Action Unit Memory Network (AUMN) for weakly supervised temporal action localization, which can mitigate the above two challenges by learning an action unit memory bank.
Ranked #6 on
Weakly Supervised Action Localization
on THUMOS14
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
Face forgery detection is raising ever-increasing interest in computer vision since facial manipulation technologies cause serious worries.
Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
Additionally, based on the ensemble of iterative predictions, we propose a self-training method which can learn from unlabeled images effectively.
Explainable Person Re-Identification with Attribute-guided Metric Distillation
In this paper, we propose a post-hoc method, named Attribute-guided Metric Distillation (AMD), to explain existing ReID models.
Ranked #44 on
Person Re-Identification
on DukeMTMC-reID
Task-Aware Part Mining Network for Few-Shot Learning
The task-aware part filters can adapt to any individual task and automatically mine task-related local parts even for an unseen task.
Foreground Activation Maps for Weakly Supervised Object Localization
To the best of our knowledge, this is the first work that can achieve remarkable performance for both tasks by optimizing them jointly via FAM for WSOL.
Meta-Attack: Class-Agnostic and Model-Agnostic Physical Adversarial Attack
To tackle these issues, we propose a class-agnostic and model-agnostic physical adversarial attack model (Meta-Attack), which is able to not only generate robust physical adversarial examples by simulating color and shape distortions, but also generalize to attacking novel images and novel DNN models by accessing a few digital and physical images.
Overcoming Language Priors with Self-supervised Learning for Visual Question Answering
Our method can compensate for the data biases by generating balanced data without introducing external annotations.
Hierarchical Granularity Transfer Learning
In this paper, we introduce a new task, named Hierarchical Granularity Transfer Learning (HGTL), to recognize sub-level categories with basic-level annotations and semantic descriptions for hierarchical categories.
CatGCN: Graph Convolutional Networks with Categorical Node Features
In this paper, we propose a new GCN model named CatGCN, which is tailored for graph learning when the node features are categorical.
Depth image denoising using nuclear norm and learning graph model
The depth images denoising are increasingly becoming the hot research topic nowadays because they reflect the three-dimensional (3D) scene and can be applied in various fields of computer vision.
Curriculum Learning for Natural Language Understanding
With the great success of pre-trained language models, the pretrain-finetune paradigm now becomes the undoubtedly dominant solution for natural language understanding (NLU) tasks.
Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning
Then, an attentional graph attribute embedding is proposed to reduce the semantic bias between seen and unseen categories, which utilizes the graph operation to capture the semantic relationship between categories.
How to Retrain Recommender System? A Sequential Meta-Learning Method
Nevertheless, normal training on new data only may easily cause overfitting and forgetting issues, since the new data is of a smaller scale and contains fewer information on long-term user preference.
ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection
Then a novel Local Orthogonal Texture-aware Module (LOTM) models the local texture information of proposal features in two orthogonal directions and represents text region with a set of contour points.
Graph Structured Network for Image-Text Matching
The GSMN explicitly models object, relation and attribute as a structured phrase, which not only allows to learn correspondence of object, relation and attribute separately, but also benefits to learn fine-grained correspondence of structured phrase.
Ranked #14 on
Cross-Modal Retrieval
on Flickr30k
Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning
Recent methods focus on learning a unified semantic-aligned visual representation to transfer knowledge between two domains, while ignoring the effect of semantic-free visual representation in alleviating the biased recognition problem.
Multi-Objective Matrix Normalization for Fine-grained Visual Recognition
In this paper, we propose an efficient Multi-Objective Matrix Normalization (MOMN) method that can simultaneously normalize a bilinear representation in terms of square-root, low-rank, and sparsity.
Bilinear Graph Neural Network with Neighbor Interactions
We term this framework as Bilinear Graph Neural Network (BGNN), which improves GNN representation ability with bilinear interactions between neighbor nodes.
LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
We propose a new model named LightGCN, including only the most essential component in GCN -- neighborhood aggregation -- for collaborative filtering.
Ranked #6 on
Recommendation Systems
on Yelp2018
Asymmetric GAN for Unpaired Image-to-image Translation
While in situations where two domains are asymmetric in complexity, i. e., the amount of information between two domains is different, these approaches pose problems of poor generation quality, mapping ambiguity, and model sensitivity.
Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
HAKE is inspired by the fact that concentric circles in the polar coordinate system can naturally reflect the hierarchy.
Ranked #1 on
Knowledge Graph Completion
on WN18RR
Scheduled Differentiable Architecture Search for Visual Recognition
Moreover, we enlarge the search space of SDAS particularly for video recognition by devising several unique operations to encode spatio-temporal dynamics and demonstrate the impact in affecting the architecture search of SDAS.
ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths
Nowadays U-net-like FCNs predominate various biomedical image segmentation applications and attain promising performance, largely due to their elegant architectures, e. g., symmetric contracting and expansive paths as well as lateral skip-connections.
Domain-Specific Embedding Network for Zero-Shot Recognition
In contrast to previous methods, the DSEN decomposes the domain-shared projection function into one domain-invariant and two domain-specific sub-functions to explore the similarities and differences between two domains.
Consensus Feature Network for Scene Parsing
However, classification networks are dominated by the discriminative portion, so directly applying classification networks to scene parsing will result in inconsistent parsing predictions within one instance and among instances of the same category.
Dense Scale Network for Crowd Counting
The key component of our network is the dense dilated convolution block, in which each dilation layer is densely connected with the others to preserve information from continuously varied scales.
Context-Aware Visual Policy Network for Fine-Grained Image Captioning
With the maturity of visual detection techniques, we are more ambitious in describing visual content with open-vocabulary, fine-grained and free-form language, i. e., the task of image captioning.
Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendation
In this work, we propose Relational Collaborative Filtering (RCF), a general framework to exploit multiple relations between items in recommender system.
Not All Words are Equal: Video-specific Information Loss for Video Captioning
To address this issue, we propose a novel learning strategy called Information Loss, which focuses on the relationship between the video-specific visual content and corresponding representative words.
CGNet: A Light-weight Context Guided Network for Semantic Segmentation
To tackle this problem, we propose a novel Context Guided Network (CGNet), which is a light-weight and efficient network for semantic segmentation.
Ranked #8 on
Semantic Segmentation
on EventScape
CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
An appearance network is developed to learn appearance features from the full body, horizontal and vertical body parts of pedestrians with spatial dependencies among body parts.
Style Separation and Synthesis via Generative Adversarial Networks
The S3-GAN consists of an encoder network, a generator network, and an adversarial network.
Context-Aware Visual Policy Network for Sequence-Level Image Captioning
To fill the gap, we propose a Context-Aware Visual Policy network (CAVP) for sequence-level image captioning.
A Two-Stream Mutual Attention Network for Semi-supervised Biomedical Segmentation with Noisy Labels
\begin{abstract} Learning-based methods suffer from a deficiency of clean annotations, especially in biomedical segmentation.
Multi-Level Policy and Reward Reinforcement Learning for Image Captioning
Image captioning is one of the most challenging hallmarks of AI, due to its complexity in visual and natural language understanding.
Time Matters: Multi-scale Temporalization of Social Media Popularity
We evaluate our approach on two large-scale Flickr image datasets with over 1. 8 million photos in total, for the task of popularity prediction.
Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks
With a joint embedding network, we obtain a unified deep representation of multi-modal user-post data in a common embedding space.
Multimodal Fusion with Recurrent Neural Networks for Rumor Detection on Microblogs
In this paper, we propose a novel Recurrent Neural Network with an at- tention mechanism (att-RNN) to fuse multimodal features for e ective rumor detection.
Scale-Adaptive Convolutions for Scene Parsing
Through adding a new scale regression layer, we can dynamically infer the position-adaptive scale coefficients which are adopted to resize the convolutional patches.
APE-GAN: Adversarial Perturbation Elimination with GAN
Although neural networks could achieve state-of-the-art performance while recongnizing images, they often suffer a tremendous defeat from adversarial examples--inputs generated by utilizing imperceptible but intentional perturbation to clean samples from the datasets.
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 #93 on
Person Re-Identification
on Market-1501
One-Shot Fine-Grained Instance Retrieval
Aiming to conquer this issue, we propose a retrieval task named One-Shot Fine-Grained Instance Retrieval (OSFGIR).
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.
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.
Image Credibility Analysis with Effective Domain Transferred Deep Networks
In order to overcome the scarcity of training samples of fake images, we first construct a large-scale auxiliary dataset indirectly related to this task.
AC-BLSTM: Asymmetric Convolutional Bidirectional LSTM Networks for Text Classification
Recently deeplearning models have been shown to be capable of making remarkable performance in sentences and documents classification tasks.
Scene-adaptive Coded Apertures Imaging
Firstly, we capture the scene with a pinhole and analyze the scene content to determine primary edge orientations.
Multi-Task Deep Visual-Semantic Embedding for Video Thumbnail Selection
Given the tremendous growth of online videos, video thumbnail, as the common visualization form of video content, is becoming increasingly important to influence user's browsing and searching experience.
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.
