Search Results for author:
Found 294 papers, 147 papers with code
Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification
Experimental results demonstrate that our DCML method explores credible and valuable training data and improves the performance of unsupervised domain adaptation.
Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?
Specifically, we disentangle the video representation into the temporal coherence and motion parts and randomly change the scale of the temporal motion features as the adversarial noise.
BMInf: An Efficient Toolkit for Big Model Inference and Tuning
In recent years, large-scale pre-trained language models (PLMs) containing billions of parameters have achieved promising results on various NLP tasks.
Unsupervised Dependency Graph Network
We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task.
Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss Correction
In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems.
RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining
Large-scale pretrained language models have achieved SOTA results on NLP tasks.
Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach
In recent years, pre-trained language models (PLMs) have been shown to capture factual knowledge from massive texts, which encourages the proposal of PLM-based knowledge graph completion (KGC) models.
Selecting Stickers in Open-Domain Dialogue through Multitask Learning
With the increasing popularity of online chatting, stickers are becoming important in our online communication.
Dual Context-Guided Continuous Prompt Tuning for Few-Shot Learning
Prompt-based paradigm has shown its competitive performance in many NLP tasks.
Spatial Geometric Reasoning for Room Layout Estimation via Deep Reinforcement Learning
Unlike most existing works that define room layout on a 2D image, we model the layout in 3D as a configuration of the camera and the room.
Rotation-robust Intersection over Union for 3D Object Detection
In this paper, we propose a Rotation-robust Intersection over Union ($ extit{RIoU}$) for 3D object detection, which aims to jointly learn the overlap of rotated bounding boxes.
Deep Hashing with Active Pairwise Supervision
n this paper, we propose a Deep Hashing method with Active Pairwise Supervision(DH-APS).
CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the Wild
Existing relation extraction (RE) methods typically focus on extracting relational facts between entity pairs within single sentences or documents.
Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation
To address the above issues, we propose a dual-generative model, Dual-Emp, to simultaneously construct the emotional consensus and utilize some external unpaired data.
欺骗类动词的句法语义研究(On the Syntax and Semantics of Verbs of Cheating)
“欺骗是一种常见的社会现象, 但对欺骗类动词的研究十分有限。本文筛选“欺骗”类动词的单句并对其进行大规模的句法依存和语义依存分析。研究显示,“欺骗”类动词在句中作为从属词时, 可作为不同的句法成分和语义角色, 同时此类动词在句法功能上表现出高度的相似性。作为支配词的“欺骗”类动词, 承担不同句法功能时, 表现出不同的句法共现模式。语义上, 本文详细描述、解释了该类动词在语义密度、主客体角色、情境角色和事件关系等维度的语义依存特点。“欺骗”类动词的句法语义虽具有多样性, 但主要的句型为主谓宾句式, 而该句式中最常用的语义搭配模式是施事对涉事进行欺骗行为, 并对涉事产生影响。本研究结合依存语法和框架语义学, 融合定量统计和定性分析探究欺骗类动词的句法语义, 深化了对欺骗行为言语线索以及言说动词的研究。”
MovieChats: Chat like Humans in a Closed Domain
In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots.
Structural Deep Metric Learning for Room Layout Estimation
We employ a metric model and a layout encoder to map the RGB images and the ground-truth layouts to the embedding space, respectively, and a layout decoder to map the embeddings to the corresponding layouts, where the whole framework is trained in an end-to-end manner.
Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation
Here, we deal with these issues on two aspects: (1) We enhance the prior selection module with the necessary posterior information obtained from the specially designed Posterior Information Prediction Module (PIPM); (2) We propose a Knowledge Distillation Based Training Strategy (KDBTS) to train the decoder with the knowledge selected from the prior distribution, removing the exposure bias of knowledge selection.
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving
Specifically, BEVerse first performs shared feature extraction and lifting to generate 4D BEV representations from multi-timestamp and multi-view images.
Introspective Deep Metric Learning
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images.
Scheduled Multi-task Learning for Neural Chat Translation
Neural Chat Translation (NCT) aims to translate conversational text into different languages.
Gait Recognition in the Wild: A Benchmark
In this paper, we contribute a new benchmark for Gait REcognition in the Wild (GREW).
Monocular 3D Fingerprint Reconstruction and Unwarping
Compared with contact-based fingerprint acquisition techniques, contactless acquisition has the advantages of less skin distortion, larger fingerprint area, and hygienic acquisition.
Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledge
Conversational Causal Emotion Entailment aims to detect causal utterances for a non-neutral targeted utterance from a conversation.
CUP: Curriculum Learning based Prompt Tuning for Implicit Event Argument Extraction
Implicit event argument extraction (EAE) aims to identify arguments that could scatter over the document.
Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting
Prior research has mainly resorted to heuristic rule-based constraints to reduce the noise for specific self-augmentation methods individually.
Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training
Firstly, we discover that the success of magnitude pruning can be attributed to the preserved pre-training performance, which correlates with the downstream transferability.
WebFace260M: A Benchmark for Million-Scale Deep Face Recognition
For a comprehensive evaluation of face matchers, three recognition tasks are performed under standard, masked and unbiased settings, respectively.
Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation
Generating adversarial examples for Neural Machine Translation (NMT) with single Round-Trip Translation (RTT) has achieved promising results by releasing the meaning-preserving restriction.
HyperDet3D: Learning a Scene-conditioned 3D Object Detector
A bathtub in a library, a sink in an office, a bed in a laundry room -- the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar objects.
SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
In this paper, we propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras.
FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment
Most existing action quality assessment methods rely on the deep features of an entire video to predict the score, which is less reliable due to the non-transparent inference process and poor interpretability.
Relational Reasoning Over Spatial-Temporal Graphs for Video Summarization
Then, we construct a temporal graph by using the aggregated representations of spatial graphs.
Ranked #1 on
Video Summarization
on TvSum
CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation
Existing reference-free metrics have obvious limitations for evaluating controlled text generation models.
Attributable Visual Similarity Learning
This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and explainable similarity measure between images.
LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection
In this paper, we propose the LiDAR Distillation to bridge the domain gap induced by different LiDAR beams for 3D object detection.
Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos
The generated text prompts are paired with corresponding video clips, and together co-train the text encoder and the video encoder via a contrastive approach.
Ranked #1 on
Action Segmentation
on 50 Salads
Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion
Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory prediction system to model the multi-modality of future motion states.
A Survey on Cross-Lingual Summarization
Cross-lingual summarization is the task of generating a summary in one language (e. g., English) for the given document(s) in a different language (e. g., Chinese).
Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene
Visual dialog has witnessed great progress after introducing various vision-oriented goals into the conversation, especially such as GuessWhich and GuessWhat, where the only image is visible by either and both of the questioner and the answerer, respectively.
ELLE: Efficient Lifelong Pre-training for Emerging Data
We experiment ELLE with streaming data from 5 domains on BERT and GPT.
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement
In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i. e. annotations of object centers).
A Variational Hierarchical Model for Neural Cross-Lingual Summarization
The goal of the cross-lingual summarization (CLS) is to convert a document in one language (e. g., English) to a summary in another one (e. g., Chinese).
Towards Robust Online Dialogue Response Generation
Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-world practice, especially in multi-turn settings.
Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation
Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e. g., token frequency or mutual information).
TSAM: A Two-Stream Attention Model for Causal Emotion Entailment
Causal Emotion Entailment (CEE) aims to discover the potential causes behind an emotion in a conversational utterance.
MSCTD: A Multimodal Sentiment Chat Translation Dataset
In this work, we introduce a new task named Multimodal Chat Translation (MCT), aiming to generate more accurate translations with the help of the associated dialogue history and visual context.
Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation
Most dominant neural machine translation (NMT) models are restricted to make predictions only according to the local context of preceding words in a left-to-right manner.
ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization
We present ClidSum, a benchmark dataset for building cross-lingual summarization systems on dialogue documents.
ApolloRL: a Reinforcement Learning Platform for Autonomous Driving
We introduce ApolloRL, an open platform for research in reinforcement learning for autonomous driving.
Mental Health Assessment for the Chatbots
Previous researches on dialogue system assessment usually focus on the quality evaluation (e. g. fluency, relevance, etc) of responses generated by the chatbots, which are local and technical metrics.
Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution
To improve matching efficiency, we design a novel Embedded PatchMacth scheme with random samples propagation, which involves end-to-end training with asymptotic linear computational cost to the input size.
Efficient Non-Local Contrastive Attention for Image Super-Resolution
To demonstrate the effectiveness of ENLCA, we build an architecture called Efficient Non-Local Contrastive Network (ENLCN) by adding a few of our modules in a simple backbone.
Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network
We show that by integrating the BALI fields and SCPA model into a novel self-calibrated pose attention network, more facial prior knowledge can be learned and the detection accuracy and robustness of our method for faces with large poses and heavy occlusions have been improved.
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network
It results in a serious issue of lagged gradient, making the learned attack at the current step ineffective due to the architecture changes afterward.
Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models
As many fine-tuned pre-trained language models~(PLMs) with promising performance are generously released, investigating better ways to reuse these models is vital as it can greatly reduce the retraining computational cost and the potential environmental side-effects.
DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
In this work, we present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP.
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers.
Ranked #8 on
3D Point Cloud Classification
on ScanObjectNN
On Transferability of Prompt Tuning for Natural Language Processing
To explore whether we can improve PT via prompt transfer, we empirically investigate the transferability of soft prompts across different downstream tasks and PLMs in this work.
Natural Language Understanding
Pretrained Language Models
+1
Deep Asymmetric Hashing with Dual Semantic Regression and Class Structure Quantization
Recently, deep hashing methods have been widely used in image retrieval task.
Exploring Universal Intrinsic Task Subspace via Prompt Tuning
In the experiments, we study diverse few-shot NLP tasks and surprisingly find that in a 250-dimensional subspace found with 100 tasks, by only tuning 250 free parameters, we can recover 97% and 83% of the full prompt tuning performance for 100 seen tasks (using different training data) and 20 unseen tasks, respectively, showing great generalization ability of the found intrinsic task subspace.
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models
Motivated by this observation, we construct a word-based robustness-aware perturbation to distinguish poisoned samples from clean samples to defend against the backdoor attacks on natural language processing (NLP) models.
Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings
Dominant sentence ordering models can be classified into pairwise ordering models and set-to-sequence models.
WeTS: A Benchmark for Translation Suggestion
To break this limitation, we create a benchmark data set for TS, called \emph{WeTS}, which contains golden corpus annotated by expert translators on four translation directions.
Topology-Imbalance Learning for Semi-Supervised Node Classification
The class imbalance problem, as an important issue in learning node representations, has drawn increasing attention from the community.
MoEfication: Transformer Feed-forward Layers are Mixtures of Experts
In this work, we study the computational patterns of FFNs and observe that most inputs only activate a tiny ratio of neurons of FFNs.
Simulated annealing for optimization of graphs and sequences
The key idea is to integrate powerful neural networks into metaheuristics (e. g., simulated annealing, SA) to restrict the search space in discrete optimization.
Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search
In this paper, we propose a Shapley value based operation contribution evaluation method (Shapley-NAS) for neural architecture search.
Structure-Preserving Image Super-Resolution
Firstly, we propose SPSR with gradient guidance (SPSR-G) by exploiting gradient maps of images to guide the recovery in two aspects.
Dynamic Knowledge Distillation for Pre-trained Language Models
Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models.
GoG: Relation-aware Graph-over-Graph Network for Visual Dialog
Specifically, GoG consists of three sequential graphs: 1) H-Graph, which aims to capture coreference relations among dialog history; 2) History-aware Q-Graph, which aims to fully understand the question through capturing dependency relations between words based on coreference resolution on the dialog history; and 3) Question-aware I-Graph, which aims to capture the relations between objects in an image based on fully question representation.
Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation
Visual dialogue is a challenging task since it needs to answer a series of coherent questions on the basis of understanding the visual environment.
Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation
To address the above issues, we propose a dual-generative model, Dual-Emp, to simultaneously construct the emotion consensus and utilize some external unpaired data.
Structure-Enhanced Pop Music Generation via Harmony-Aware Learning
Besides, when chords evolve into chord progression, the texture and the form can be bridged by the harmony naturally, which contributes to the joint learning of the two structures.
Different Strokes for Different Folks: Investigating Appropriate Further Pre-training Approaches for Diverse Dialogue Tasks
Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing.
Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder
(2) RAR forces the model to reconstruct the original sample from its adversarial representation.
Challenging Instances are Worth Learning: Generating Valuable Negative Samples for Response Selection Training
In this way, our negative instances are fluent, context-related, and more challenging for the model to learn, while can not be positive.
Competence-based Curriculum Learning for Multilingual Machine Translation
Therefore, we focus on balancing the learning competencies of different languages and propose Competence-based Curriculum Learning for Multilingual Machine Translation, named CCL-M.
Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical
To address this, we propose a Star-shaped Reasoning Graph Network (S-RGN).
Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser
To enhance VD Questioner: 1) we propose a Related entity enhanced Questioner (ReeQ) that generates questions under the guidance of related entities and learns entity-based questioning strategy from human dialogs; 2) we propose an Augmented Guesser (AugG) that is strong and is optimized for the VD setting especially.
Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark
Compared to previous dialogue tasks, MOD is much more challenging since it requires the model to understand the multimodal elements as well as the emotions behind them.
Towards Making the Most of Dialogue Characteristics for Neural Chat Translation
Neural Chat Translation (NCT) aims to translate conversational text between speakers of different languages.
NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
In this work, we present a new multi-view depth estimation method that utilizes both conventional reconstruction and learning-based priors over the recently proposed neural radiance fields (NeRF).
Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification
Data augmentation aims to enrich training samples for alleviating the overfitting issue in low-resource or class-imbalanced situations.
Scheduled Sampling Based on Decoding Steps for Neural Machine Translation
Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus bridging the gap between training and inference.
Deep Relational Metric Learning
This paper presents a deep relational metric learning (DRML) framework for image clustering and retrieval.
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
Unlike most existing methods that learn visual attention based on conventional likelihood, we propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process.
Ranked #4 on
Fine-Grained Image Classification
on FGVC Aircraft
PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr that adopts a transformer encoder-decoder architecture for point cloud completion.
Ranked #1 on
Point Cloud Completion
on ShapeNet
Group-aware Contrastive Regression for Action Quality Assessment
Assessing action quality is challenging due to the subtle differences between videos and large variations in scores.
Ranked #1 on
Action Quality Assessment
on MTL-AQA
RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection
In particular, we propose to generate random layouts of a scene by making use of the objects in the synthetic CAD dataset and learn the 3D scene representation by applying object-level contrastive learning on two random scenes generated from the same set of synthetic objects.
Masked Face Recognition Challenge: The WebFace260M Track Report
There are second phase of the challenge till October 1, 2021 and on-going leaderboard.
Towards Interpretable Deep Metric Learning with Structural Matching
Our method is model-agnostic, which can be applied to off-the-shelf backbone networks and metric learning methods.
Ranked #12 on
Metric Learning
on CUB-200-2011
PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management
Therefore, we proposed a system called PatrickStar to lower the hardware requirements of PTMs and make them accessible to everyone.
Person Re-identification via Attention Pyramid
Experimental results demonstrate the superiority of our method, which outperforms the state-of-the-art methods by a large margin with limited computational cost.
Ranked #13 on
Person Re-Identification
on MSMT17
Generalizable Mixed-Precision Quantization via Attribution Rank Preservation
On the contrary, our GMPQ searches the mixed-quantization policy that can be generalized to largescale datasets with only a small amount of data, so that the search cost is significantly reduced without performance degradation.
WeChat Neural Machine Translation Systems for WMT21
This paper introduces WeChat AI's participation in WMT 2021 shared news translation task on English->Chinese, English->Japanese, Japanese->English and English->German.
SimpModeling: Sketching Implicit Field to Guide Mesh Modeling for 3D Animalmorphic Head Design
In this work, we propose SimpModeling, a novel sketch-based system for helping users, especially amateur users, easily model 3D animalmorphic heads - a prevalent kind of heads in character design.
Instance Similarity Learning for Unsupervised Feature Representation
In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation.
Rethinking Stealthiness of Backdoor Attack against NLP Models
In this work, we point out a potential problem of current backdoor attacking research: its evaluation ignores the stealthiness of backdoor attacks, and most of existing backdoor attacking methods are not stealthy either to system deployers or to system users.
Human Trajectory Prediction via Counterfactual Analysis
Most existing methods learn to predict future trajectories by behavior clues from history trajectories and interaction clues from environments.
Modeling Bilingual Conversational Characteristics for Neural Chat Translation
Despite the impressive performance of sentence-level and context-aware Neural Machine Translation (NMT), there still remain challenges to translate bilingual conversational text due to its inherent characteristics such as role preference, dialogue coherence, and translation consistency.
Confidence-Aware Scheduled Sampling for Neural Machine Translation
In this way, the model is exactly exposed to predicted tokens for high-confidence positions and still ground-truth tokens for low-confidence positions.
Target-Oriented Fine-tuning for Zero-Resource Named Entity Recognition
In this paper, we tackle the problem by transferring knowledge from three aspects, i. e., domain, language and task, and strengthening connections among them.
Modeling Explicit Concerning States for Reinforcement Learning in Visual Dialogue
In Reinforcement Learning, it is crucial to represent states and assign rewards based on the action-caused transitions of states.
Similarity-Aware Fusion Network for 3D Semantic Segmentation
To address this, we employ a late fusion strategy where we first learn the geometric and contextual similarities between the input and back-projected (from 2D pixels) point clouds and utilize them to guide the fusion of two modalities to further exploit complementary information.
Ranked #10 on
Semantic Segmentation
on ScanNet
Global Filter Networks for Image Classification
Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision have shown great potential in achieving promising performance with fewer inductive biases.
Ranked #8 on
Image Classification
on Stanford Cars
(using extra training data)
Rethinking the Evaluation of Neural Machine Translation
However, this evaluation framework suffers from high search errors brought by heuristic search algorithms and is limited by its nature of evaluation over one best candidate.
Deep Compositional Metric Learning
In this paper, we propose a deep compositional metric learning (DCML) framework for effective and generalizable similarity measurement between images.
Structure-Aware Face Clustering on a Large-Scale Graph With 107 Nodes
To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method.
Pseudo Facial Generation With Extreme Poses for Face Recognition
Many of them settle it by generating fake frontal faces from extreme ones, whereas they are tough to maintain the identity information with high computational consumption and uncontrolled disturbances.
Self-Supervised Video Hashing via Bidirectional Transformers
Most existing unsupervised video hashing methods are built on unidirectional models with less reliable training objectives, which underuse the correlations among frames and the similarity structure between videos.
Sequence-Level Training for Non-Autoregressive Neural Machine Translation
Non-Autoregressive Neural Machine Translation (NAT) removes the autoregressive mechanism and achieves significant decoding speedup through generating target words independently and simultaneously.
Evaluating Modules in Graph Contrastive Learning
The recent emergence of contrastive learning approaches facilitates the research on graph representation learning (GRL), introducing graph contrastive learning (GCL) into the literature.
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation
In this paper, however, we observe that although distilling the teacher's hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled.
GTM: A Generative Triple-Wise Model for Conversational Question Generation
Generating some appealing questions in open-domain conversations is an effective way to improve human-machine interactions and lead the topic to a broader or deeper direction.
Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency
Employing human judges to interact with chatbots on purpose to check their capacities is costly and low-efficient, and difficult to get rid of subjective bias.
Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances
Nowadays, open-domain dialogue models can generate acceptable responses according to the historical context based on the large-scale pre-trained language models.
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
Based on this observation, we propose a dynamic token sparsification framework to prune redundant tokens progressively and dynamically based on the input.
Ranked #181 on
Image Classification
on ImageNet
Exploring Dynamic Selection of Branch Expansion Orders for Code Generation
Due to the great potential in facilitating software development, code generation has attracted increasing attention recently.
Context Tracking Network: Graph-based Context Modeling for Implicit Discourse Relation Recognition
Implicit discourse relation recognition (IDRR) aims to identify logical relations between two adjacent sentences in the discourse.
Fully Hyperbolic Neural Networks
Hyperbolic neural networks have shown great potential for modeling complex data.
CLEVE: Contrastive Pre-training for Event Extraction
Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning.
Knowledge Inheritance for Pre-trained Language Models
Specifically, we introduce a pre-training framework named "knowledge inheritance" (KI) and explore how could knowledge distillation serve as auxiliary supervision during pre-training to efficiently learn larger PLMs.
Selective Knowledge Distillation for Neural Machine Translation
As an active research field in NMT, knowledge distillation is widely applied to enhance the model's performance by transferring teacher model's knowledge on each training sample.
Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation
Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training weights to different tokens, in order to alleviate the token imbalance problem.
Prevent the Language Model from being Overconfident in Neural Machine Translation
The Neural Machine Translation (NMT) model is essentially a joint language model conditioned on both the source sentence and partial translation.
Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction
Distantly supervised (DS) relation extraction (RE) has attracted much attention in the past few years as it can utilize large-scale auto-labeled data.
FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection
To tackle this problem, we propose frustum-aware geometric reasoning (FGR) to detect vehicles in point clouds without any 3D annotations.
ER-IQA: Boosting Perceptual Quality Assessment Using External Reference Images
In this paper, we introduce a brand new scheme, namely external-reference image quality assessment (ER-IQA), by introducing external reference images to bridge the gap between FR and NR-IQA.
SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation
To make a better trade-off between accuracy and efficiency, we propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE).
Objects are Different: Flexible Monocular 3D Object Detection
The precise localization of 3D objects from a single image without depth information is a highly challenging problem.
Ranked #3 on
Monocular 3D Object Detection
on KITTI Cars Moderate
Is ``hot pizza'' Positive or Negative? Mining Target-aware Sentiment Lexicons
Modelling a word{'}s polarity in different contexts is a key task in sentiment analysis.
Meta-Mining Discriminative Samples for Kinship Verification
In the end, the samples in the unbalanced train batch are re-weighted by the learned meta-miner to optimize the kinship models.
Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
An ordinal distribution constraint is proposed to exploit the ordinal nature of regression.
Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes
To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method.
WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol.
Ranked #1 on
Face Verification
on IJB-C
(dataset metric)
Epidemic spreading under pathogen evolution
Specifically, we detect a new pandemic phase - the mutated phase - in which, despite the fact that the pathogen is initially non-pandemic (R0 < 1), it may still spread due to the emergence of a critical mutation.
Separable Structure Modeling for Semi-supervised Video Object Segmentation
Specifically, we first compute a pixel-wise similarity matrix by using representations of reference and target pixels and then select top-rank reference pixels for target pixel classification.
One-shot visual object segmentation
Video Semantic Segmentation
CSS-LM: A Contrastive Framework for Semi-supervised Fine-tuning of Pre-trained Language Models
We then perform contrastive semi-supervised learning on both the retrieved unlabeled and original labeled instances to help PLMs capture crucial task-related semantic features.
MAX Phase Zr2SeC and Its Thermal Conduction Behavior
The elemental diversity is crucial to screen out ternary MAX phases with outstanding properties via tuning of bonding types and strength between constitutive atoms.
Materials Science
Rank-Consistency Deep Hashing for Scalable Multi-Label Image Search
As hashing becomes an increasingly appealing technique for large-scale image retrieval, multi-label hashing is also attracting more attention for the ability to exploit multi-level semantic contents.
Retro-Reflective Beam Communications with Spatially Separated Laser Resonator
Optical wireless communications (OWC) utilizing infrared or visible light as the carrier attracts great attention in 6G research.
WeChat AI & ICT's Submission for DSTC9 Interactive Dialogue Evaluation Track
We participate in the DSTC9 Interactive Dialogue Evaluation Track (Gunasekara et al. 2020) sub-task 1 (Knowledge Grounded Dialogue) and sub-task 2 (Interactive Dialogue).
SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images
In this paper, we first introduce the concept of semantic objectness to exploit the geometric relationship of these two tasks through an analysis of the imaging process, then propose a Semantic Object Segmentation and Depth Estimation Network (SOSD-Net) based on the objectness assumption.
Ranked #39 on
Semantic Segmentation
on NYU Depth v2
Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds
Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in feature extraction, leading to misclassification in the transition area between two objects.
Weakly-Supervised Saliency Detection via Salient Object Subitizing
This allows the supervision to be aligned with the property of saliency detection, where the salient objects of an image could be from more than one class.
Frequency-Aware Spatiotemporal Transformers for Video Inpainting Detection
In this paper, we propose a frequency-aware spatiotemporal transformers for deep In this paper, we propose a Frequency-Aware Spatiotemporal Transformer (FAST) for video inpainting detection, which aims to simultaneously mine the traces of video inpainting from spatial, temporal, and frequency domains.
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning
Pre-trained Language Models (PLMs) have shown superior performance on various downstream Natural Language Processing (NLP) tasks.
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade
On the other hand, the exiting decisions made by internal classifiers are unreliable, leading to wrongly emitted early predictions.
SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation
Most existing point cloud instance and semantic segmentation methods rely heavily on strong supervision signals, which require point-level labels for every point in the scene.
Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification
Graph Contrastive Learning (GCL) has proven highly effective in promoting the performance of Semi-Supervised Node Classification (SSNC).
Emotional Conversation Generation with Heterogeneous Graph Neural Network
Firstly, we design a Heterogeneous Graph-Based Encoder to represent the conversation content (i. e., the dialogue history, its emotion flow, facial expressions, audio, and speakers' personalities) with a heterogeneous graph neural network, and then predict suitable emotions for feedback.