Search Results for author:
Found 215 papers, 89 papers with code
SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition
Arbitrary text appearance poses a great challenge in scene text recognition tasks.
ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information
Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding.
Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks
Factorization Machines (FMs) are a supervised learning approach that enhances the linear regression model by incorporating the second-order feature interactions.
A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications
Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.
Federated Mutual Learning
The experiments show that FML can achieve better performance than alternatives in typical FL setting, and clients can be benefited from FML with different models and tasks.
You Only Recognize Once: Towards Fast Video Text Spotting
Video text spotting is still an important research topic due to its various real-applications.
Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
Many approaches have recently been proposed to detect irregular scene text and achieved promising results.
Ranked #8 on
Text Spotting
on SCUT-CTW1500
TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
Since real-world ubiquitous documents (e. g., invoices, tickets, resumes and leaflets) contain rich information, automatic document image understanding has become a hot topic.
MANGO: A Mask Attention Guided One-Stage Scene Text Spotter
Recently end-to-end scene text spotting has become a popular research topic due to its advantages of global optimization and high maintainability in real applications.
Ranked #6 on
Text Spotting
on SCUT-CTW1500
Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition
In this work, we excavate the implicit task, character counting within the traditional text recognition, without additional labor annotation cost.
LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment
In this paper, we aim to obtain more reliable aligned bounding boxes by fully utilizing the visual information from both text regions in proposed local features and cell relations in global features.
Ranked #7 on
Table Recognition
on PubTabNet
VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations
To address the above limitations, we propose a unified framework VSR for document layout analysis, combining vision, semantics and relations.
Ranked #3 on
Document Layout Analysis
on PubLayNet val
A Unified MRC Framework for Named Entity Recognition
Instead of treating the task of NER as a sequence labeling problem, we propose to formulate it as a machine reading comprehension (MRC) task.
Ranked #2 on
Nested Mention Recognition
on ACE 2004
(using extra training data)
Chinese Named Entity Recognition
Entity Extraction using GAN
+4
FcaNet: Frequency Channel Attention Networks
With the proof, we naturally generalize the compression of the channel attention mechanism in the frequency domain and propose our method with multi-spectral channel attention, termed as FcaNet.
DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis
To these ends, we propose a simpler but more effective Deep Fusion Generative Adversarial Networks (DF-GAN).
Ranked #4 on
Text-to-Image Generation
on CUB
(Inception score metric)
Dice Loss for Data-imbalanced NLP Tasks
Many NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly outnumber positive examples, and the huge number of background examples (or easy-negative examples) overwhelms the training.
Ranked #1 on
Chinese Named Entity Recognition
on OntoNotes 4
(using extra training data)
Chinese Named Entity Recognition
Machine Reading Comprehension
+5
BertGCN: Transductive Text Classification by Combining GCN and BERT
In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification.
Ranked #1 on
Text Classification
on 20 Newsgroups
Deep Sequence Learning with Auxiliary Information for Traffic Prediction
Predicting traffic conditions from online route queries is a challenging task as there are many complicated interactions over the roads and crowds involved.
Ranked #1 on
Traffic Prediction
on Q-Traffic
Dependency Parsing as MRC-based Span-Span Prediction
The proposed method has the following merits: (1) it addresses the fundamental problem that edges in a dependency tree should be constructed between subtrees; (2) the MRC framework allows the method to retrieve missing spans in the span proposal stage, which leads to higher recall for eligible spans.
GPT-NER: Named Entity Recognition via Large Language Models
GPT-NER bridges the gap by transforming the sequence labeling task to a generation task that can be easily adapted by LLMs e. g., the task of finding location entities in the input text "Columbus is a city" is transformed to generate the text sequence "@@Columbus## is a city", where special tokens @@## marks the entity to extract.
Coreference Resolution as Query-based Span Prediction
In this paper, we present an accurate and extensible approach for the coreference resolution task.
CorefQA: Coreference Resolution as Query-based Span Prediction
In this paper, we present CorefQA, an accurate and extensible approach for the coreference resolution task.
Ranked #2 on
Coreference Resolution
on CoNLL 2012
(using extra training data)
OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
Based on this dataset, we propose a family of encoder-decoder models leveraging both textual and visual contexts, from coarse-grained image features extracted from CNNs to fine-grained object features extracted from Faster R-CNNs.
Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation
Specifically, we propose to model the mutual dependency between text-visual features, where the model not only needs to learn the probability of generating the next dialog utterance given preceding dialog utterances and visual contexts, but also the probability of predicting the visual features in which a dialog utterance takes place, leading the generated dialog utterance specific to the visual context.
KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
(2) A dynamic weighting strategy named Consensus Focus to identify both the malicious and irrelevant domains.
Knowledge Distillation
Multi-Source Unsupervised Domain Adaptation
+2
Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations.
Instruction Tuning for Large Language Models: A Survey
This paper surveys research works in the quickly advancing field of instruction tuning (IT), a crucial technique to enhance the capabilities and controllability of large language models (LLMs).
Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI
However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed.
Self-Explaining Structures Improve NLP Models
The proposed model comes with the following merits: (1) span weights make the model self-explainable and do not require an additional probing model for interpretation; (2) the proposed model is general and can be adapted to any existing deep learning structures in NLP; (3) the weight associated with each text span provides direct importance scores for higher-level text units such as phrases and sentences.
OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction
We start to collect 1, 800 common household objects and annotate their affordances to construct the first knowledge base: Oak.
Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining
The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make the best use of U is poorly understood: is semi-supervised learning still beneficial with the presence of large-scale pretraining?
Ranked #1000000000 on
Text Classification
on IMDb
Text Classification via Large Language Models
This is due to (1) the lack of reasoning ability in addressing complex linguistic phenomena (e. g., intensification, contrast, irony etc); (2) limited number of tokens allowed in in-context learning.
InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks.
TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
Arbitrary-shaped text detection is a challenging task due to the complex geometric layouts of texts such as large aspect ratios, various scales, random rotations and curve shapes.
Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space.
Learning Dynamic Context Augmentation for Global Entity Linking
Despite of the recent success of collective entity linking (EL) methods, these "global" inference methods may yield sub-optimal results when the "all-mention coherence" assumption breaks, and often suffer from high computational cost at the inference stage, due to the complex search space.
Ranked #5 on
Entity Disambiguation
on AIDA-CoNLL
GNN-LM: Language Modeling based on Global Contexts via GNN
Inspired by the notion that ``{\it to copy is easier than to memorize}``, in this work, we introduce GNN-LM, which extends the vanilla neural language model (LM) by allowing to reference similar contexts in the entire training corpus.
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
RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning
To the best of our awareness, RoSA is the first work focuses on the non-aligned node-node graph contrastive learning problem.
HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
To further capture human characteristics, we propose a structure-invariant alignment loss that enforces different masked views, guided by the human part prior, to be closely aligned for the same image.
Fast Nearest Neighbor Machine Translation
Fast $k$NN-MT constructs a significantly smaller datastore for the nearest neighbor search: for each word in a source sentence, Fast $k$NN-MT first selects its nearest token-level neighbors, which is limited to tokens that are the same as the query token.
Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning
To systematically measure the compositional generalizability of temporal grounding models, we introduce a new Compositional Temporal Grounding task and construct two new dataset splits, i. e., Charades-CG and ActivityNet-CG.
DeVLBert: Learning Deconfounded Visio-Linguistic Representations
In this paper, we propose to investigate the problem of out-of-domain visio-linguistic pretraining, where the pretraining data distribution differs from that of downstream data on which the pretrained model will be fine-tuned.
Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer
In this paper, we propose a method to increase the accuracy of a ground camera's location and orientation by estimating the relative rotation and translation between the ground-level image and its matched/retrieved satellite image.
Instrumental Variables in Causal Inference and Machine Learning: A Survey
This paper serves as the first effort to systematically and comprehensively introduce and discuss the IV methods and their applications in both causal inference and machine learning.
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.
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.
DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization
DUET is deployed on a powerful cloud server that only requires the low cost of forwarding propagation and low time delay of data transmission between the device and the cloud.
Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution
Convolutional neural networks based single-image super-resolution (SISR) has made great progress in recent years.
SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite
However, existing public datasets do not include images obtained by drones at different heights, and the types of scenes are relatively homogeneous, which yields issues in assessing a model's capability to adapt to complex and changing scenes.
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.
CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction
The journey of reducing noise from distant supervision (DS) generated training data has been started since the DS was first introduced into the relation extraction (RE) task.
Memory Regulation and Alignment toward Generalizer RGB-Infrared Person
The domain shift, coming from unneglectable modality gap and non-overlapped identity classes between training and test sets, is a major issue of RGB-Infrared person re-identification.
Cross-relation Cross-bag Attention for Distantly-supervised Relation Extraction
Distant supervision leverages knowledge bases to automatically label instances, thus allowing us to train relation extractor without human annotations.
Learning Decomposed Representation for Counterfactual Inference
The fundamental problem in treatment effect estimation from observational data is confounder identification and balancing.
Why Do We Click: Visual Impression-aware News Recommendation
In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation.
Homogeneous and Heterogeneous Relational Graph for Visible-infrared Person Re-identification
Existing VI Re-ID methods mainly focus on extracting homogeneous structural relationships in an image, i. e. the relations between local features, while ignoring the heterogeneous correlation of local features in different modalities.
Triggerless Backdoor Attack for NLP Tasks with Clean Labels
To deal with this issue, in this paper, we propose a new strategy to perform textual backdoor attacks which do not require an external trigger, and the poisoned samples are correctly labeled.
Goal-Oriented Prompt Attack and Safety Evaluation for LLMs
There are several black-box attack methods, such as Prompt Attack, which can change the behaviour of LLMs and induce LLMs to generate unexpected answers with harmful contents.
Poet: Product-oriented Video Captioner for E-commerce
Then, based on the aspects of the video-associated product, we perform knowledge-enhanced spatial-temporal inference on those graphs for capturing the dynamic change of fine-grained product-part characteristics.
Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition
We also learn confounder representations by encouraging them to be relevant to both the treatment and the outcome.
Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation
Specifically, Re4 encapsulates three backward flows, i. e., 1) Re-contrast, which drives each interest embedding to be distinct from other interests using contrastive learning; 2) Re-attend, which ensures the interest-item correlation estimation in the forward flow to be consistent with the criterion used in final recommendation; and 3) Re-construct, which ensures that each interest embedding can semantically reflect the information of representative items that relate to the corresponding interest.
ModelGPT: Unleashing LLM's Capabilities for Tailored Model Generation
The rapid advancement of Large Language Models (LLMs) has revolutionized various sectors by automating routine tasks, marking a step toward the realization of Artificial General Intelligence (AGI).
Comprehensive Information Integration Modeling Framework for Video Titling
In e-commerce, consumer-generated videos, which in general deliver consumers' individual preferences for the different aspects of certain products, are massive in volume.
Future-Aware Diverse Trends Framework for Recommendation
By diverse trends, supposing the future preferences can be diversified, we propose the diverse trends extractor and the time-aware mechanism to represent the possible trends of preferences for a given user with multiple vectors.
Domain-Specific Bias Filtering for Single Labeled Domain Generalization
In this paper, we investigate a Single Labeled Domain Generalization (SLDG) task with only one source domain being labeled, which is more practical and challenging than the CDG task.
Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps
To fulfill the direct evaluation, we annotate pixel-level object masks on the ILSVRC validation set.
Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images
The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data.
ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos
A recent benchmark AGQA poses a promising paradigm to generate QA pairs automatically from pre-annotated scene graphs, enabling it to measure diverse reasoning abilities with granular control.
Leaning Compact and Representative Features for Cross-Modality Person Re-Identification
This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task, which aims to match pedestrian samples between visible and infrared modes.
Cross-Modality Person Re-identification
Knowledge Distillation
+1
An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
We present Expert-Token-Routing, a unified generalist framework that facilitates seamless integration of multiple expert LLMs.
Informative Visual Storytelling with Cross-modal Rules
To solve this problem, we propose a method to mine the cross-modal rules to help the model infer these informative concepts given certain visual input.
Ranked #11 on
Visual Storytelling
on VIST
Collaborative Semantic Aggregation and Calibration for Federated Domain Generalization
Domain generalization (DG) aims to learn from multiple known source domains a model that can generalize well to unknown target domains.
Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual Samples
To verify this hypothesis, we manually construct a set of counterfactual samples, which modify the original logical forms to generate counterfactual logical forms with rarely co-occurred table headers and logical operators.
$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection
For a task with $k$ training labels, $k$Folden induces $k$ sub-models, each of which is trained on a subset with $k-1$ categories with the left category masked unknown to the sub-model.
Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction
Given the fact description text of a legal case, legal judgment prediction (LJP) aims to predict the case's charge, law article and penalty term.
AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
However, simply adopting models derived from DFKD for real-world applications suffers significant performance degradation, due to the discrepancy between teachers' training data and real-world scenarios (student domain).
KCAT: A Knowledge-Constraint Typing Annotation Tool
Fine-grained Entity Typing is a tough task which suffers from noise samples extracted from distant supervision.
Leveraging Model Interpretability and Stability to increase Model Robustness
We then use an error detector in the form of a binary classifier on top of the DNN to automatically discriminate wrong and correct predictions of the DNN based on their hidden unit activations.
SemGloVe: Semantic Co-occurrences for GloVe from BERT
In this paper, we propose SemGloVe, which distills semantic co-occurrences from BERT into static GloVe word embeddings.
Learning Instrumental Variable from Data Fusion for Treatment Effect Estimation
The advent of the big data era brought new opportunities and challenges to draw treatment effect in data fusion, that is, a mixed dataset collected from multiple sources (each source with an independent treatment assignment mechanism).
AMD-HookNet for Glacier Front Segmentation
are present in the data), which exacerbates the difficulty of accurate segmentation.
Ranked #1 on
Calving Front Delineation In Synthetic Aperture Radar Imagery With Fixed Training Amount
on CaFFe
Calving Front Delineation In Synthetic Aperture Radar Imagery With Fixed Training Amount
Segmentation
From Graph to Word Bag: Introducing Domain Knowledge to Confusing Charge Prediction
In this paper, we introduce a novel From Graph to Word Bag (FWGB) approach, which introduces domain knowledge regarding constituent elements to guide the model in making judgments on confusing charges, much like a judge's reasoning process.
Enhancing Court View Generation with Knowledge Injection and Guidance
Court View Generation (CVG) is a challenging task in the field of Legal Artificial Intelligence (LegalAI), which aims to generate court views based on the plaintiff claims and the fact descriptions.
Distribution-based Label Space Transformation for Multi-label Learning
This endows DLST the capability to handle label set sparsity and training data sparsity in multi-label learning problems.
State Distribution-aware Sampling for Deep Q-learning
A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution.
A Semantic QA-Based Approach for Text Summarization Evaluation
In this paper, we will present some preliminary results on one especially useful and challenging problem in NLP system evaluation: how to pinpoint content differences of two text passages (especially for large pas-sages such as articles and books).
Find the Conversation Killers: a Predictive Study of Thread-ending Posts
In this study, we are particularly interested in identifying a post in a multi-party conversation that is unlikely to be further replied to, which therefore kills that thread of the conversation.
Representation Learning for Scale-free Networks
Existing network embedding works primarily focus on preserving the microscopic structure, such as the first- and second-order proximity of vertexes, while the macroscopic scale-free property is largely ignored.
Group-wise Deep Co-saliency Detection
In this paper, we propose an end-to-end group-wise deep co-saliency detection approach to address the co-salient object discovery problem based on the fully convolutional network (FCN) with group input and group output.
Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection
As a result, a key issue in video saliency detection is how to effectively capture the intrinsical properties of atomic video structures as well as their associated contextual interactions along the spatial and temporal dimensions.
Transductive Zero-Shot Learning with a Self-training dictionary approach
As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data.
DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner.
Deep Learning Driven Visual Path Prediction from a Single Image
The highly effective visual representation and deep context models ensure that our framework makes a deep semantic understanding of the scene and motion pattern, consequently improving the performance of the visual path prediction task.
Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning
In this paper, we propose a new approach, namely Hierarchical Recurrent Neural Encoder (HRNE), to exploit temporal information of videos.
Metric Learning Driven Multi-Task Structured Output Optimization for Robust Keypoint Tracking
As an important and challenging problem in computer vision and graphics, keypoint-based object tracking is typically formulated in a spatio-temporal statistical learning framework.
Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions
We validate the effectiveness of our ASST on two large-scale datasets.
Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images
As a fundamental and challenging problem in computer vision, hand pose estimation aims to estimate the hand joint locations from depth images.
Textually Guided Ranking Network for Attentional Image Retweet Modeling
In this paper, we study the problem of image retweet prediction in social media, which predicts the image sharing behavior that the user reposts the image tweets from their followees.
Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection
Finally, we transform the output of recurrent neural network into the corresponding action distribution.
Bi-Adversarial Auto-Encoder for Zero-Shot Learning
Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from the visual features to the class semantics, which fails to construct the visual-semantic interactions well.
NITE: A Neural Inductive Teaching Framework for Domain Specific NER
In domain-specific NER, due to insufficient labeled training data, deep models usually fail to behave normally.
Super-Resolution Person Re-Identification With Semi-Coupled Low-Rank Discriminant Dictionary Learning
In this paper, we propose a semi-coupled low-rank discriminant dictionary learning (SLD^2L) approach for SR person re-identification.
Reinforcement Learning for Optimal Load Distribution Sequencing in Resource-Sharing System
Divisible Load Theory (DLT) is a powerful tool for modeling divisible load problems in data-intensive systems.
Posterior-regularized REINFORCE for Instance Selection in Distant Supervision
This paper provides a new way to improve the efficiency of the REINFORCE training process.
Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net
Segmentation of pancreas is important for medical image analysis, yet it faces great challenges of class imbalance, background distractions and non-rigid geometrical features.
Galaxy Learning -- A Position Paper
Model training, as well as the communication, is achieved with blockchain and its smart contracts.
Walking with MIND: Mental Imagery eNhanceD Embodied QA
The experimental results and further analysis prove that the agent with the MIND module is superior to its counterparts not only in EQA performance but in many other aspects such as route planning, behavioral interpretation, and the ability to generalize from a few examples.
Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization
The second module is a specific classifier for mining trivial or incomplete action regions, which is trained on the shared features after erasing the seeded regions activated by SSG.
Action Detection
Weakly-supervised Temporal Action Localization
+1
Large-scale Pretraining for Neural Machine Translation with Tens of Billions of Sentence Pairs
In this paper, we investigate the problem of training neural machine translation (NMT) systems with a dataset of more than 40 billion bilingual sentence pairs, which is larger than the largest dataset to date by orders of magnitude.
Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation
Visual navigation is a task of training an embodied agent by intelligently navigating to a target object (e. g., television) using only visual observations.
LAVA NAT: A Non-Autoregressive Translation Model with Look-Around Decoding and Vocabulary Attention
Non-autoregressive translation (NAT) models generate multiple tokens in one forward pass and is highly efficient at inference stage compared with autoregressive translation (AT) methods.
Description Based Text Classification with Reinforcement Learning
We observe significant performance boosts over strong baselines on a wide range of text classification tasks including single-label classification, multi-label classification and multi-aspect sentiment analysis.
Non-Autoregressive Neural Dialogue Generation
Unfortunately, under the framework of the \sts model, direct decoding from $\log p(y|x) + \log p(x|y)$ is infeasible since the second part (i. e., $p(x|y)$) requires the completion of target generation before it can be computed, and the search space for $y$ is enormous.
Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units
Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e. g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states).
Grounded and Controllable Image Completion by Incorporating Lexical Semantics
Existing image completion procedure is highly subjective by considering only visual context, which may trigger unpredictable results which are plausible but not faithful to a grounded knowledge.
SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
In this way, the model is able to select the most salient nodes and reduce the quadratic complexity regardless of the sequence length.
Progressive Multi-Stage Learning for Discriminative Tracking
Visual tracking is typically solved as a discriminative learning problem that usually requires high-quality samples for online model adaptation.
Spatiotemporal graph routing for skeleton-based action recognition
With the representation effectiveness, skeleton-based human action recognition has received considerable research attention, and has a wide range of real applications.
Object-QA: Towards High Reliable Object Quality Assessment
In this paper, we define the problem of object quality assessment for the first time and propose an effective approach named Object-QA to assess high-reliable quality scores for object images.
Analyzing COVID-19 on Online Social Media: Trends, Sentiments and Emotions
At the time of writing, the ongoing pandemic of coronavirus disease (COVID-19) has caused severe impacts on society, economy and people's daily lives.
Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis
Infectious keratitis is the most common entities of corneal diseases, in which pathogen grows in the cornea leading to inflammation and destruction of the corneal tissues.
ResKD: Residual-Guided Knowledge Distillation
In this paper, we see knowledge distillation in a fresh light, using the knowledge gap, or the residual, between a teacher and a student as guidance to train a much more lightweight student, called a res-student.
Balance-Subsampled Stable Prediction
However, this assumption is often violated in practice because the sample selection bias may induce the distribution shift from training data to test data.
Stable Prediction via Leveraging Seed Variable
By assuming the relationships between causal variables and response variable are invariant across data, to address this problem, we propose a conditional independence test based algorithm to separate those causal variables with a seed variable as priori, and adopt them for stable prediction.
MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning
As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and fast adaptation to new knowledge.
Learning a Domain Classifier Bank for Unsupervised Adaptive Object Detection
To tackle this issue, we develop a fine-grained domain alignment approach with a well-designed domain classifier bank that achieves the instance-level alignment respecting to their categories.
Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism
This is even more laborious when generating images with very different views.
Memory Efficient Class-Incremental Learning for Image Classification
To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer.
Topic Adaptation and Prototype Encoding for Few-Shot Visual Storytelling
In this paper, we focus on enhancing the generalization ability of the VIST model by considering the few-shot setting.
Two Step Joint Model for Drug Drug Interaction Extraction
When patients need to take medicine, particularly taking more than one kind of drug simultaneously, they should be alarmed that there possibly exists drug-drug interaction.
Drug–drug Interaction Extraction
named-entity-recognition
+4
Improving Robustness and Generality of NLP Models Using Disentangled Representations
We show that models trained with the proposed criteria provide better robustness and domain adaptation ability in a wide range of supervised learning tasks.
MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination
In this paper, we investigate the problem of text-to-pedestrian synthesis, which has many potential applications in art, design, and video surveillance.
Intriguing class-wise properties of adversarial training
Adversarial training is one of the most effective approaches to improve model robustness against adversarial examples.
Rethinking Pseudo-labeled Sample Mining for Semi-Supervised Object Detection
However, the impact of the pseudo-labeled samples' quality as well as the mining strategies for high quality training sample have rarely been studied in SSL.
Pair the Dots: Jointly Examining Training History and Test Stimuli for Model Interpretability
Any prediction from a model is made by a combination of learning history and test stimuli.
De-Biased Court's View Generation with Causality
Court{'}s view generation is a novel but essential task for legal AI, aiming at improving the interpretability of judgment prediction results and enabling automatic legal document generation.
VersatileGait: A Large-Scale Synthetic Gait Dataset with Fine-GrainedAttributes and Complicated Scenarios
With the motivation of practical gait recognition applications, we propose to automatically create a large-scale synthetic gait dataset (called VersatileGait) by a game engine, which consists of around one million silhouette sequences of 11, 000 subjects with fine-grained attributes in various complicated scenarios.
Learning to Anticipate Egocentric Actions by Imagination
We further improve ImagineRNN by residual anticipation, i. e., changing its target to predicting the feature difference of adjacent frames instead of the frame content.
Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning.
JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution
In this work, we treat the mask occlusion as image noise and construct a joint and collaborative learning network, called JDSR-GAN, for the masked face super-resolution task.
Modeling High-order Interactions across Multi-interests for Micro-video Recommendation
Personalized recommendation system has become pervasive in various video platform.
Sentence Similarity Based on Contexts
The proposed framework is based on the core idea that the meaning of a sentence should be defined by its contexts, and that sentence similarity can be measured by comparing the probabilities of generating two sentences given the same context.
Polar Relative Positional Encoding for Video-Language Segmentation
In this paper, we propose a novel Polar Relative Positional Encoding (PRPE) mechanism that represents spatial relations in a ``linguistic'' way, i. e., in terms of direction and range.
Ranked #11 on
Referring Expression Segmentation
on J-HMDB
Federated Graph Learning -- A Position Paper
Federated learning (FL) is a an emerging technique that can collaboratively train a shared model while keeping the data decentralized, which is a rational solution for distributed GNN training.
Analysis and Applications of Class-wise Robustness in Adversarial Training
Adversarial training is one of the most effective approaches to improve model robustness against adversarial examples.
Parameter Estimation for the SEIR Model Using Recurrent Nets
Next, based on this recurrent net that is able to generalize SEIR simulations, we are able to transform the objective to a differentiable one with respect to $\Theta_\text{SEIR}$, and straightforwardly obtain its optimal value.
Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning
Specifically, Shapley Value and its desired properties are leveraged in deep MARL to credit any combinations of agents, which grants us the capability to estimate the individual credit for each agent.
Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference
Secondly, we introduce semantic coherence learning to explicitly encourage the semantic coherence of the adaptive hierarchical graph network from three hierarchies.
ICDAR 2021 Competition on Scene Video Text Spotting
During the competition period (opened on 1st March, 2021 and closed on 11th April, 2021), a total of 24 teams participated in the three proposed tasks with 46 valid submissions, respectively.
Layer-wise Model Pruning based on Mutual Information
The proposed pruning strategy offers merits over weight-based pruning techniques: (1) it avoids irregular memory access since representations and matrices can be squeezed into their smaller but dense counterparts, leading to greater speedup; (2) in a manner of top-down pruning, the proposed method operates from a more global perspective based on training signals in the top layer, and prunes each layer by propagating the effect of global signals through layers, leading to better performances at the same sparsity level.
ConRPG: Paraphrase Generation using Contexts as Regularizer
A long-standing issue with paraphrase generation is how to obtain reliable supervision signals.
Paraphrase Generation as Unsupervised Machine Translation
Then based on the paraphrase pairs produced by these UMT models, a unified surrogate model can be trained to serve as the final \sts model to generate paraphrases, which can be directly used for test in the unsupervised setup, or be finetuned on labeled datasets in the supervised setup.
CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
In this paper, we propose to learn accurate and robust user representations, which are required to be less sensitive to (attack on) noisy behaviors and trust more on the indispensable ones, by modeling counterfactual data distribution.
Instrumental Variable-Driven Domain Generalization with Unobserved Confounders
Meanwhile, the existing of unobserved confounders which affect the input features and labels simultaneously cause spurious correlation and hinder the learning of the invariant relationship contained in the conditional distribution.
Semi-Supervised Active Learning for Semi-Supervised Models: Exploit Adversarial Examples With Graph-Based Virtual Labels
Although current mainstream methods begin to combine SSL and AL (SSL-AL) to excavate the diverse expressions of unlabeled samples, these methods' fully supervised task models are still trained only with labeled data.
Stable Prediction on Graphs with Agnostic Distribution Shift
The results demonstrate that our method outperforms various SOTA GNNs for stable prediction on graphs with agnostic distribution shift, including shift caused by node labels and attributes.
Multi-trends Enhanced Dynamic Micro-video Recommendation
In this paper, we propose the DMR framework to explicitly model dynamic multi-trends of users' current preference and make predictions based on both the history and future potential trends.
Minimizing Memorization in Meta-learning: A Causal Perspective
Meta-learning has emerged as a potent paradigm for quick learning of few-shot tasks, by leveraging the meta-knowledge learned from meta-training tasks.
Treatment effect estimation with confounder balanced instrumental variable regression
In this paper, we propose a Confounder Balanced IV Regression (CB-IV) algorithm to jointly remove the bias from the unmeasured confounders with IV regression and reduce the bias from the observed confounders by balancing for treatment effect estimation.
kFolden: k-Fold Ensemble for Out-Of-Distribution Detection
Out-of-Distribution (OOD) detection is an important problem in natural language processing (NLP).
Dialogue Inspectional Summarization with Factual Inconsistency Awareness
Dialogue summarization has been extensively studied and applied, where the prior works mainly focused on exploring superior model structures to align the input dialogue and the output summary.
Unified Group Fairness on Federated Learning
We validate the advantages of the FMDA-M algorithm with various kinds of distribution shift settings in experiments, and the results show that FMDA-M algorithm outperforms the existing fair FL algorithms on unified group fairness.
Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training
In contrast to existing solutions, the implementation of the SageMaker library is much more generic and flexible, in that it can automatically partition and run pipeline parallelism over arbitrary model architectures with minimal code change, and also offers a general and extensible framework for tensor parallelism, which supports a wider range of use cases, and is modular enough to be easily applied to new training scripts.
A General Framework for Defending Against Backdoor Attacks via Influence Graph
In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a \textsc{specific} type of attacking pattern, and therefore, poisoned training examples have greater impacts on each other during training.
CGIBNet: Bandwidth-constrained Communication with Graph Information Bottleneck in Multi-Agent Reinforcement Learning
The node information compression aims to address the problem of what to communicate via learning compact node representations.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation
A common problem in both pruning and distillation is to determine compressed architecture, i. e., the exact number of filters per layer and layer configuration, in order to preserve most of the original model capacity.
End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding
To achieve effective grounding under a limited annotation budget, we investigate one-shot video grounding, and learn to ground natural language in all video frames with solely one frame labeled, in an end-to-end manner.
Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning
Walle consists of a deployment platform, distributing ML tasks to billion-scale devices in time; a data pipeline, efficiently preparing task input; and a compute container, providing a cross-platform and high-performance execution environment, while facilitating daily task iteration.
Collaborative Intelligence Orchestration: Inconsistency-Based Fusion of Semi-Supervised Learning and Active Learning
Motivated by the industry practice of labeling data, we propose an innovative Inconsistency-based virtual aDvErsarial Active Learning (IDEAL) algorithm to further investigate SSL-AL's potential superiority and achieve mutual enhancement of AL and SSL, i. e., SSL propagates label information to unlabeled samples and provides smoothed embeddings for AL, while AL excludes samples with inconsistent predictions and considerable uncertainty for SSL.
Intelligent Request Strategy Design in Recommender System
RSs typically put a large number of items into one page to reduce excessive resource consumption from numerous paging requests, which, however, would diminish the RSs' ability to timely renew the recommendations according to users' real-time interest and lead to a poor user experience.
Knowledge Distillation of Transformer-based Language Models Revisited
In the past few years, transformer-based pre-trained language models have achieved astounding success in both industry and academia.
E2-AEN: End-to-End Incremental Learning with Adaptively Expandable Network
In this paper, we propose an end-to-end trainable adaptively expandable network named E2-AEN, which dynamically generates lightweight structures for new tasks without any accuracy drop in previous tasks.
TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents
Most existing methods divide this task into two subparts: the text reading part for obtaining the plain text from the original document images and the information extraction part for extracting key contents.
Label-Efficient Domain Generalization via Collaborative Exploration and Generalization
To escape from the dilemma between domain generalization and annotation costs, in this paper, we introduce a novel task named label-efficient domain generalization (LEDG) to enable model generalization with label-limited source domains.
CCL4Rec: Contrast over Contrastive Learning for Micro-video Recommendation
Micro-video recommender systems suffer from the ubiquitous noises in users' behaviors, which might render the learned user representation indiscriminating, and lead to trivial recommendations (e. g., popular items) or even weird ones that are far beyond users' interests.
Personalizing Intervened Network for Long-tailed Sequential User Behavior Modeling
In this paper, we propose a novel approach that significantly improves the recommendation performance of the tail users while achieving at least comparable performance for the head users over the base model.
Learning Individual Treatment Effects under Heterogeneous Interference in Networks
In network data, due to interference, the outcome of a unit is influenced not only by its treatment (i. e., direct effects) but also by others' treatments (i. e., spillover effects).
Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing
Neural-symbolic computing (NeSy), which pursues the integration of the symbolic and statistical paradigms of cognition, has been an active research area of Artificial Intelligence (AI) for many years.
Confounder Balancing for Instrumental Variable Regression with Latent Variable
This paper studies the confounding effects from the unmeasured confounders and the imbalance of observed confounders in IV regression and aims at unbiased causal effect estimation.
ConfounderGAN: Protecting Image Data Privacy with Causal Confounder
The success of deep learning is partly attributed to the availability of massive data downloaded freely from the Internet.
ParallelNet: Multi-mode Trajectory Prediction by Multi-mode Trajectory Fusion
Level 5 Autonomous Driving, a technology that a fully automated vehicle (AV) requires no human intervention, has raised serious concerns on safety and stability before widespread use.
Depth Estimation maps of lidar and stereo images
The structure of this paper is made of by following:(1) Performance: to discuss and evaluate about depth maps created from stereo images and 3D cloud points, and relationships analysis for alignment and errors;(2) Depth estimation by stereo images: to explain the methods about how to use stereo images to estimate depth;(3)Depth estimation by lidar: to explain the methods about how to use 3d cloud datas to estimate depth;In summary, this report is mainly to show the performance of depth maps and their approaches, analysis for them.
Multi Lane Detection
Lane detection is a long-standing task and a basic module in autonomous driving.
Group Sparse Coding for Image Denoising
Group sparse representation has shown promising results in image debulrring and image inpainting in GSR [3] , the main reason that lead to the success is by exploiting Sparsity and Nonlocal self-similarity (NSS) between patches on natural images, and solve a regularized optimization problem.
Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding
To systematically benchmark the compositional generalizability of temporal grounding models, we introduce a new Compositional Temporal Grounding task and construct two new dataset splits, i. e., Charades-CG and ActivityNet-CG.
DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation
In recommendation scenarios, there are two long-standing challenges, i. e., selection bias and data sparsity, which lead to a significant drop in prediction accuracy for both Click-Through Rate (CTR) and post-click Conversion Rate (CVR) tasks.
IDEAL: Toward High-efficiency Device-Cloud Collaborative and Dynamic Recommendation System
The aforementioned two trends enable the device-cloud collaborative and dynamic recommendation, which deeply exploits the recommendation pattern among cloud-device data and efficiently characterizes different instances with different underlying distributions based on the cost of frequent device-cloud communication.
Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary
Thus we propose to separate the identity features with the variance features in a light-weighted set-based disentanglement framework.
RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction
In addition, we propose RexUIE, which is a Recursive Method with Explicit Schema Instructor for UIE.
Denoising Multi-modal Sequential Recommenders with Contrastive Learning
In contrast, modalities that do not cause users' behaviors are potential noises and might mislead the learning of a recommendation model.
Generalized Universal Domain Adaptation with Generative Flow Networks
We introduce a new problem in unsupervised domain adaptation, termed as Generalized Universal Domain Adaptation (GUDA), which aims to achieve precise prediction of all target labels including unknown categories.
WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding
WINNER first builds the language decomposition tree in a bottom-up manner, upon which the structural attention mechanism and top-down feature backtracking jointly build a multi-modal decomposition tree, permitting a hierarchical understanding of unstructured videos.
Quantitatively Measuring and Contrastively Exploring Heterogeneity for Domain Generalization
With contrastive learning, we propose a learning potential-guided metric for domain heterogeneity by promoting learning variant features.
Pushing the Limits of ChatGPT on NLP Tasks
In this work, we propose a collection of general modules to address these issues, in an attempt to push the limits of ChatGPT on NLP tasks.
DisCover: Disentangled Music Representation Learning for Cover Song Identification
We analyze the CSI task in a disentanglement view with the causal graph technique, and identify the intra-version and inter-version effects biasing the invariant learning.
MEDOE: A Multi-Expert Decoder and Output Ensemble Framework for Long-tailed Semantic Segmentation
The proposed two-sage framework comprises a multi-expert decoder (MED) and a multi-expert output ensemble (MOE).
Hierarchical Topological Ordering with Conditional Independence Test for Limited Time Series
Learning directed acyclic graphs (DAGs) to identify causal relations underlying observational data is crucial but also poses significant challenges.
Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration
Precedents are the previous legal cases with similar facts, which are the basis for the judgment of the subsequent case in national legal systems.
