Search Results for author:
Found 111 papers, 52 papers with code
Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning
Class imbalance distribution widely exists in real-world engineering.
Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
In this paper, we introduce a novel contrastive action representation learning (CARL) framework to learn frame-wise action representations, especially for long videos, in a self-supervised manner.
Linearizing Transformer with Key-Value Memory Bank
We propose MemSizer, an approach also projects the source sequence into lower dimension representation but can take input with dynamic length, with a different perspective of the attention mechanism.
CLRNet: Cross Layer Refinement Network for Lane Detection
In this way, we can exploit more contextual information to detect lanes while leveraging local detailed lane features to improve localization accuracy.
Ranked #1 on
Lane Detection
on CULane
Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion
Different from prior works, we propose a new RoI fusion strategy 3D-GAF (3D Grid-wise Attentive Fusion) to make fuller use of information from different types of point clouds.
WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection
This network is learned by minimizing our newly-proposed 3D alignment loss between the 3D box estimates and the corresponding RoI LiDAR points.
Measuring and Reducing Model Update Regression in Structured Prediction for NLP
First, we measure and analyze model update regression in different model update settings.
A Survey on Retrieval-Augmented Text Generation
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community.
TopNet: Learning from Neural Topic Model to Generate Long Stories
In particular, instead of directly generating a story, we first learn to map the short text input to a low-dimensional topic distribution (which is pre-assigned by a topic model).
Exploring Dense Retrieval for Dialogue Response Selection
In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using a dense retrieval model.
Multilingual AMR Parsing with Noisy Knowledge Distillation
We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher.
Digging Into Output Representation for Monocular 3D Object Detection
This characteristic indicates that monocular 3D detection is inherently different from other typical detection tasks that have the same dimensional input and output.
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems.
Exploiting Reasoning Chains for Multi-hop Science Question Answering
We propose a novel Chain Guided Retriever-reader ({\tt CGR}) framework to model the reasoning chain for multi-hop Science Question Answering.
ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding
%To facilitate the research on ASR-robust general language understanding, In this paper, we propose ASR-GLUE benchmark, a new collection of 6 different NLU tasks for evaluating the performance of models under ASR error across 3 different levels of background noise and 6 speakers with various voice characteristics.
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention
On the one hand, CEL blends each embedding with multiple patches of different scales, providing the self-attention module itself with cross-scale features.
Ranked #26 on
Semantic Segmentation
on ADE20K val
Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification
Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks not seen during training, given only a few examples.
Attacking Adversarial Attacks as A Defense
In this work, we find that the adversarial attacks can also be vulnerable to small perturbations.
Salient Object Ranking with Position-Preserved Attention
In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency.
Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering
Our framework contains three new ideas: (a) {\tt AMR-SG}, an AMR-based Semantic Graph, constructed by candidate fact AMRs to uncover any hop relations among question, answer and multiple facts.
Neural Machine Translation with Monolingual Translation Memory
Second, the memory retriever and NMT model can be jointly optimized for the ultimate translation goal.
Assessing Dialogue Systems with Distribution Distances
An important aspect of developing dialogue systems is how to evaluate and compare the performance of different systems.
Discriminative-Generative Dual Memory Video Anomaly Detection
In this paper, we propose a DiscRiminative-gEnerative duAl Memory (DREAM) anomaly detection model to take advantage of a few anomalies and solve data imbalance.
Lidar Point Cloud Guided Monocular 3D Object Detection
In this paper, we propose LPCG (LiDAR point cloud guided monocular 3D object detection), which is a general framework for guiding the training of monocular 3D detectors with LiDAR point clouds.
OCM3D: Object-Centric Monocular 3D Object Detection
Image-only and pseudo-LiDAR representations are commonly used for monocular 3D object detection.
SCALoss: Side and Corner Aligned Loss for Bounding Box Regression
In this paper, we propose Side Overlap~(SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases.
X-view: Non-egocentric Multi-View 3D Object Detector
3D object detection algorithms for autonomous driving reason about 3D obstacles either from 3D birds-eye view or perspective view or both.
Suppress-and-Refine Framework for End-to-End 3D Object Detection
In this work, we propose a suppress-and-refine framework to remove these handcrafted components.
DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Network
In this paper, we argue that a Mutual Nearest Neighbor (MNN) relation should be established to explicitly select the query descriptors that are most relevant to each task and discard less relevant ones from aggregative clutters in FSL.
ES-Net: Erasing Salient Parts to Learn More in Re-Identification
In this paper, we propose a novel network, Erasing-Salient Net (ES-Net), to learn comprehensive features by erasing the salient areas in an image.
Non-Autoregressive Text Generation with Pre-trained Language Models
In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance.
Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification
In this paper, to complement these low recall neighbor pseudo labels, we propose a joint learning framework to learn better feature embeddings via high precision neighbor pseudo labels and high recall group pseudo labels.
Dialogue Response Selection with Hierarchical Curriculum Learning
As for IC, it progressively strengthens the model's ability in identifying the mismatching information between the dialogue context and a response candidate.
Ranked #2 on
Conversational Response Selection
on Douban
Narrative Incoherence Detection
We propose the task of narrative incoherence detection as a new arena for inter-sentential semantic understanding: Given a multi-sentence narrative, decide whether there exist any semantic discrepancies in the narrative flow.
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
Each of these small networks has a fraction of the original one's parameters.
Ranked #19 on
Image Classification
on CIFAR-10
EasyTransfer -- A Simple and Scalable Deep Transfer Learning Platform for NLP Applications
The literature has witnessed the success of leveraging Pre-trained Language Models (PLMs) and Transfer Learning (TL) algorithms to a wide range of Natural Language Processing (NLP) applications, yet it is not easy to build an easy-to-use and scalable TL toolkit for this purpose.
Geometry-based Occlusion-Aware Unsupervised Stereo Matching for Autonomous Driving
Occlusion handling is a challenging problem in stereo matching, especially for unsupervised methods.
Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation
We investigate this problem by study the gap of confidence between teacher and student.
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
Specifically, it first casts the relationships between a certain model's accuracy and depth/width/resolution into a polynomial regression and then maximizes the polynomial to acquire the optimal values for the three dimensions.
Do Wider Neural Networks Really Help Adversarial Robustness?
Previous empirical results suggest that adversarial training requires wider networks for better performances.
RESA: Recurrent Feature-Shift Aggregator for Lane Detection
Lane detection is one of the most important tasks in self-driving.
Ranked #8 on
Lane Detection
on TuSimple
Apparel-invariant Feature Learning for Apparel-changed Person Re-identification
Therefore, it is critical to learn an apparel-invariant person representation under cases like cloth changing or several persons wearing similar clothes.
Interpretable Real-Time Win Prediction for Honor of Kings, a Popular Mobile MOBA Esport
With the rapid prevalence and explosive development of MOBA esports (Multiplayer Online Battle Arena electronic sports), much research effort has been devoted to automatically predicting game results (win predictions).
Learning to Caricature via Semantic Shape Transform
Caricature is an artistic drawing created to abstract or exaggerate facial features of a person.
Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach
Our proposed model disentangles the image content from the visual attributes, and it learns to modify the latter using the textual description, before generating a new image from the content and the modified attribute representation.
Out-of-distribution Generalization via Partial Feature Decorrelation
Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting.
Adversarial Mutual Information for Text Generation
Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation.
AMR Parsing via Graph-Sequence Iterative Inference
We propose a new end-to-end model that treats AMR parsing as a series of dual decisions on the input sequence and the incrementally constructed graph.
Ranked #2 on
AMR Parsing
on LDC2014T12
(F1 Full metric)
The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection
Despite that response selection is naturally a learning-to-rank problem, most prior works take a point-wise view and train binary classifiers for this task: each response candidate is labeled either relevant (one) or irrelevant (zero).
Ranked #9 on
Conversational Response Selection
on E-commerce
Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory
A stylistic response generator then takes the prototype and the desired language style as model input to obtain a high-quality and stylistic response.
Stylistic Dialogue Generation via Information-Guided Reinforcement Learning Strategy
To enable better balance between the content quality and the style, we introduce a new training strategy, know as Information-Guided Reinforcement Learning (IG-RL).
Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds
3D object detection based on point clouds has become more and more popular.
Bi-Decoder Augmented Network for Neural Machine Translation
Neural Machine Translation (NMT) has become a popular technology in recent years, and the encoder-decoder framework is the mainstream among all the methods.
Adversarial-Learned Loss for Domain Adaptation
In order to combine the strengths of these two methods, we propose a novel method called Adversarial-Learned Loss for Domain Adaptation (ALDA).
DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration
The dominant pruning methods, filter-level pruning methods, evaluate their performance through the reduction ratio of computations and deem that a higher reduction ratio of computations is equivalent to a higher acceleration ratio in terms of inference time.
Graph Transformer for Graph-to-Sequence Learning
The dominant graph-to-sequence transduction models employ graph neural networks for graph representation learning, where the structural information is reflected by the receptive field of neurons.
PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module
Moreover, based on the PACF module, we propose a 3D multi-sensor multi-task network called Pointcloud-Image RCNN(PI-RCNN as brief), which handles the image segmentation and 3D object detection tasks.
Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework
End-to-end sequence generation is a popular technique for developing open domain dialogue systems, though they suffer from the \textit{safe response problem}.
Region Mutual Information Loss for Semantic Segmentation
In this paper, we develop a region mutual information (RMI) loss to model the dependencies among pixels more simply and efficiently.
Correlation Maximized Structural Similarity Loss for Semantic Segmentation
Inspired by the widely-used structural similarity (SSIM) index in image quality assessment, we use the linear correlation between two images to quantify their structural similarity.
Domain Adaptation for Semantic Segmentation with Maximum Squares Loss
However, when applying the entropy minimization to UDA for semantic segmentation, the gradient of the entropy is biased towards samples that are easy to transfer.
Core Semantic First: A Top-down Approach for AMR Parsing
The output graph spans the nodes by the distance to the root, following the intuition of first grasping the main ideas then digging into more details.
Ranked #19 on
AMR Parsing
on LDC2017T10
A Better Way to Attend: Attention with Trees for Video Question Answering
We propose a new attention model for video question answering.
Training-Time-Friendly Network for Real-Time Object Detection
Experiments on MS COCO show that our TTFNet has great advantages in balancing training time, inference speed, and accuracy.
Charge-Based Prison Term Prediction with Deep Gating Network
Judgment prediction for legal cases has attracted much research efforts for its practice use, of which the ultimate goal is prison term prediction.
Neural Machine Translation with Noisy Lexical Constraints
Experiments show that our approach can indeed improve the translation quality with the automatically generated constraints.
Progressive Transfer Learning
Model fine-tuning is a widely used transfer learning approach in person Re-identification (ReID) applications, which fine-tuning a pre-trained feature extraction model into the target scenario instead of training a model from scratch.
Reinforced Dynamic Reasoning for Conversational Question Generation
This paper investigates a new task named Conversational Question Generation (CQG) which is to generate a question based on a passage and a conversation history (i. e., previous turns of question-answer pairs).
Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference
We observe that people usually use some discourse markers such as "so" or "but" to represent the logical relationship between two sentences.
Ranked #12 on
Natural Language Inference
on SNLI
MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models
In this paper, we transfer knowledge learned from machine comprehension to the sequence-to-sequence tasks to deepen the understanding of the text.
Improving Semantic Segmentation via Dilated Affinity
To be specific, our method explicitly requires the network to predict semantic segmentation as well as dilated affinity, which is a sparse version of pair-wise pixel affinity.
High Dimensional Similarity Search with Satellite System Graph: Efficiency, Scalability, and Unindexed Query Compatibility
However, we find there are several limitations with NSG: 1) NSG has no theoretical guarantee on nearest neighbor search when the query is not indexed in the database; 2) NSG is too sparse which harms the search performance.
A Minimax Game for Instance based Selective Transfer Learning
To the best of our knowledge, this is the first to build a minimax game based model for selective transfer learning.
Localizing Unseen Activities in Video via Image Query
Thus, we consider a new task to localize unseen activities in videos via image queries, named Image-Based Activity Localization.
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
2) Cross-layer filter comparison is unachievable since the importance is defined locally within each layer.
Query-based Interactive Recommendation by Meta-Path and Adapted Attention-GRU
A novel query-based interactive recommender system is proposed in this paper, where \textbf{personalized questions are accurately generated from millions of automatically constructed questions} in Step 1, and \textbf{the recommendation is ensured to be closely-related to users' feedback} in Step 2.
Weakly-supervised Caricature Face Parsing through Domain Adaptation
However, current state-of-the-art face parsing methods require large amounts of labeled data on the pixel-level and such process for caricature is tedious and labor-intensive.
Chinese Word Segmentation: Another Decade Review (2007-2017)
This paper reviews the development of Chinese word segmentation (CWS) in the most recent decade, 2007-2017.
Translating a Math Word Problem to an Expression Tree
Moreover, we analyze the performance of three popular SEQ2SEQ models on the math word problem solving.
Dial2Desc: End-to-end Dialogue Description Generation
We first propose a new task named Dialogue Description (Dial2Desc).
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.
Translating a Math Word Problem to a Expression Tree
Moreover, we analyze the performance of three popular SEQ2SEQ models on the math word problem solving.
Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
Such models rely on insufficient information for generating a specific response since a certain query could be answered in multiple ways.
Language Style Transfer from Sentences with Arbitrary Unknown Styles
Then, by recombining the content with the target style, we decode a sentence aligned in the target domain.
Addressing the Item Cold-start Problem by Attribute-driven Active Learning
Both content information (e. g. item attributes) and initial user ratings are valuable for seizing users' preferences on a new item.
A Brand-level Ranking System with the Customized Attention-GRU Model
In e-commerce websites like Taobao, brand is playing a more important role in influencing users' decision of click/purchase, partly because users are now attaching more importance to the quality of products and brand is an indicator of quality.
PixelLink: Detecting Scene Text via Instance Segmentation
Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression.
Ranked #6 on
Scene Text Detection
on ICDAR 2013
On the Diversity of Realistic Image Synthesis
Experimental results show that images synthesized by our approach are significantly more diverse than that of the current existing works and equipping our diversity loss does not degrade the reality of the base networks.
A Revisit on Deep Hashings for Large-scale Content Based Image Retrieval
However, there are serious flaws in the evaluations of existing deep hashing papers: (1) The datasets they used are too small and simple to simulate the real CBIR situation.
Dialogue Act Recognition via CRF-Attentive Structured Network
Dialogue Act Recognition (DAR) is a challenging problem in dialogue interpretation, which aims to attach semantic labels to utterances and characterize the speaker's intention.
Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation
In this paper, we propose a novel neural network system that consists a Demand Optimization Model based on a passage-attention neural machine translation and a Reader Model that can find the answer given the optimized question.
Smarnet: Teaching Machines to Read and Comprehend Like Human
Machine Comprehension (MC) is a challenging task in Natural Language Processing field, which aims to guide the machine to comprehend a passage and answer the given question.
Ranked #34 on
Question Answering
on SQuAD1.1 dev
Learning Graph-Level Representation for Drug Discovery
Molecules can be represented as an undirected graph, and we can utilize graph convolution networks to predication molecular properties.
Ranked #1 on
Drug Discovery
on HIV dataset
MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
Machine comprehension(MC) style question answering is a representative problem in natural language processing.
Ranked #19 on
Question Answering
on TriviaQA
Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph
In this paper, to further improve the search-efficiency and scalability of graph-based methods, we start by introducing four aspects: (1) ensuring the connectivity of the graph; (2) lowering the average out-degree of the graph for fast traversal; (3) shortening the search path; and (4) reducing the index size.
Deep Rotation Equivariant Network
Recently, learning equivariant representations has attracted considerable research attention.
The Forgettable-Watcher Model for Video Question Answering
Then we propose a TGIF-QA dataset for video question answering with the help of automatic question generation.
Fast and Accurate Neural Word Segmentation for Chinese
Neural models with minimal feature engineering have achieved competitive performance against traditional methods for the task of Chinese word segmentation.
A Revisit of Hashing Algorithms for Approximate Nearest Neighbor Search
However, many existing hashing papers only report the performance with the code length shorter than 128.
Question Retrieval for Community-based Question Answering via Heterogeneous Network Integration Learning
The challenges in this task are the lexical gaps between questions for the word ambiguity and word mismatch problem.
User Personalized Satisfaction Prediction via Multiple Instance Deep Learning
However, it is not effective for users to attain answers within minutes.
Relational Multi-Manifold Co-Clustering
In this study, we focus on improving the co-clustering performance via manifold ensemble learning, which is able to maximally approximate the intrinsic manifolds of both the sample and feature spaces.
Constrained Low-Rank Learning Using Least Squares-Based Regularization
To achieve this goal, we cast the problem into a constrained rank minimization framework by adopting the least squares regularization.
EFANNA : An Extremely Fast Approximate Nearest Neighbor Search Algorithm Based on kNN Graph
In this paper, we propose EFANNA, an extremely fast approximate nearest neighbor search algorithm based on $k$NN Graph.
Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction
By noting that sparse SVMs induce sparsities in both feature and sample spaces, we propose a novel approach, which is based on accurate estimations of the primal and dual optima of sparse SVMs, to simultaneously identify the inactive features and samples that are guaranteed to be irrelevant to the outputs.
Neural Word Segmentation Learning for Chinese
Most previous approaches to Chinese word segmentation formalize this problem as a character-based sequence labeling task where only contextual information within fixed sized local windows and simple interactions between adjacent tags can be captured.
Depth Image Inpainting: Improving Low Rank Matrix Completion with Low Gradient Regularization
The proposed low gradient regularization is integrated with the low rank regularization into the low rank low gradient approach for depth image inpainting.
Deep Feature Based Contextual Model for Object Detection
Object detection is one of the most active areas in computer vision, which has made significant improvement in recent years.
Stereo Matching by Joint Energy Minimization
For the first step they solve a fully connected MRF model.
Compressed Hashing
Recent studies have shown that hashing methods are effective for high dimensional nearest neighbor search.
Graph Regularized Nonnegative Matrix Factorization for Data Representation
In GNMF, an affinity graph is constructed to encode the geometrical information and we seek a matrix factorization, which respects the graph structure.
