Search Results for author:
Found 502 papers, 278 papers with code
DeepTransport: Learning Spatial-Temporal Dependency for Traffic Condition Forecasting
Several pioneering approaches have been proposed based on traffic observations of the target location as well as its adjacent regions, but they obtain somewhat limited accuracy due to a lack of mining road topology.
Graph Neural Networks: A Review of Methods and Applications
Lots of learning tasks require dealing with graph data which contains rich relation information among elements.
Unleashing Text-to-Image Diffusion Models for Visual Perception
In this paper, we propose VPD (Visual Perception with a pre-trained Diffusion model), a new framework that exploits the semantic information of a pre-trained text-to-image diffusion model in visual perception tasks.
Ranked #7 on
Referring Expression Segmentation
on RefCoCo val
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction
To lift image features to the 3D TPV space, we further propose a transformer-based TPV encoder (TPVFormer) to obtain the TPV features effectively.
Ranked #1 on
Prediction Of Occupancy Grid Maps
on nuScenes
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
Based on ToolBench, we fine-tune LLaMA to obtain an LLM ToolLLaMA, and equip it with a neural API retriever to recommend appropriate APIs for each instruction.
Ranked #3 on
Trajectory Planning
on ToolBench
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.
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
For data scaling, we introduce a Warmup-Stable-Decay (WSD) learning rate scheduler (LRS), conducive to continuous training and domain adaptation.
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks.
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions
In this paper, we show that the key ingredients behind the vision Transformers, namely input-adaptive, long-range and high-order spatial interactions, can also be efficiently implemented with a convolution-based framework.
Ranked #20 on
Semantic Segmentation
on ADE20K
VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks
We hope this model can set a new baseline for generalist vision and language models.
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
The proposed method is verified with a wide spectrum of traditional and modern image backbones and achieves new SoTA results on the large-scale nuScenes dataset.
Ranked #5 on
3D Object Detection
on Rope3D
WebCPM: Interactive Web Search for Chinese Long-form Question Answering
We recruit annotators to search for relevant information using our interface and then answer questions.
PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management
PatrickStar uses the CPU-GPU heterogeneous memory space to store the model data.
FewRel 2.0: Towards More Challenging Few-Shot Relation Classification
We present FewRel 2. 0, a more challenging task to investigate two aspects of few-shot relation classification models: (1) Can they adapt to a new domain with only a handful of instances?
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving
Towards a more comprehensive perception of a 3D scene, in this paper, we propose a SurroundOcc method to predict the 3D occupancy with multi-camera images.
DocRED: A Large-Scale Document-Level Relation Extraction Dataset
Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on extracting intra-sentence relations for single entity pairs.
Ranked #59 on
Relation Extraction
on DocRED
EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education
Currently, EduChat is available online as an open-source project, with its code, data, and model parameters available on platforms (e. g., GitHub https://github. com/icalk-nlp/EduChat, Hugging Face https://huggingface. co/ecnu-icalk ).
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.
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 #3 on
Efficient ViTs
on ImageNet-1K (With LV-ViT-S)
Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks
We extend our method to hierarchical models including CNNs and hierarchical vision Transformers as well as more complex dense prediction tasks that require structured feature maps by formulating a more generic dynamic spatial sparsification framework with progressive sparsification and asymmetric computation for different spatial locations.
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
(Chamfer Distance L2 metric)
AdaPoinTr: Diverse Point Cloud Completion with Adaptive 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, which adopts a Transformer encoder-decoder architecture for point cloud completion.
Ranked #2 on
Point Cloud Completion
on ShapeNet
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 #13 on
Few-Shot 3D Point Cloud Classification
on ModelNet40 5-way (10-shot)
(using extra training data)
3D Point Cloud Linear Classification
Few-Shot 3D Point Cloud Classification
+2
Structure-Preserving Super Resolution with Gradient Guidance
In this paper, we propose a structure-preserving super resolution method to alleviate the above issue while maintaining the merits of GAN-based methods to generate perceptual-pleasant details.
Ranked #46 on
Image Super-Resolution
on Urban100 - 4x upscaling
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.
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).
DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation
In this way, the proposed DiffTalk is capable of producing high-quality talking head videos in synchronization with the source audio, and more importantly, it can be naturally generalized across different identities without any further fine-tuning.
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 #9 on
Image Classification
on Stanford Cars
(using extra training data)
A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment Analysis
The aspect-based sentiment analysis (ABSA) task remains to be a long-standing challenge, which aims to extract the aspect term and then identify its sentiment orientation. In previous approaches, the explicit syntactic structure of a sentence, which reflects the syntax properties of natural language and hence is intuitively crucial for aspect term extraction and sentiment recognition, is typically neglected or insufficiently modeled.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
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.
Ranked #15 on
Robust Camera Only 3D Object Detection
on nuScenes-C
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 #8 on
Monocular 3D Object Detection
on KITTI Cars Moderate
Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis
Thus the facial radiance field can be flexibly adjusted to the new identity with few reference images.
Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications
The advancements in speed and efficiency of DCNv4, combined with its robust performance across diverse vision tasks, show its potential as a foundational building block for future vision models.
Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation
In this paper, we propose a deep face super-resolution (FSR) method with iterative collaboration between two recurrent networks which focus on facial image recovery and landmark estimation respectively.
A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer
Therefore, in this paper, we propose a dual reinforcement learning framework to directly transfer the style of the text via a one-step mapping model, without any separation of content and style.
Ranked #1 on
Unsupervised Text Style Transfer
on GYAFC
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.
SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
Our SelfOcc outperforms the previous best method SceneRF by 58. 7% using a single frame as input on SemanticKITTI and is the first self-supervised work that produces reasonable 3D occupancy for surround cameras on nuScenes.
Improving Multi-turn Dialogue Modelling with Utterance ReWriter
To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network.
BiDet: An Efficient Binarized Object Detector
Conventional network binarization methods directly quantize the weights and activations in one-stage or two-stage detectors with constrained representational capacity, so that the information redundancy in the networks causes numerous false positives and degrades the performance significantly.
GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification
Fact verification (FV) is a challenging task which requires to retrieve relevant evidence from plain text and use the evidence to verify given claims.
Ranked #7 on
Fact Verification
on FEVER
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.
MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer
Developing generative models for interleaved image-text data has both research and practical value.
Diffusion-SDF: Text-to-Shape via Voxelized Diffusion
With the rising industrial attention to 3D virtual modeling technology, generating novel 3D content based on specified conditions (e. g. text) has become a hot issue.
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.
Hardness-Aware Deep Metric Learning
This paper presents a hardness-aware deep metric learning (HDML) framework.
Ranked #30 on
Metric Learning
on CUB-200-2011
(using extra training data)
MAVEN: A Massive General Domain Event Detection Dataset
Most existing datasets exhibit the following issues that limit further development of ED: (1) Data scarcity.
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.
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 #8 on
Vehicle Re-Identification
on VehicleID Medium
LOGO: A Long-Form Video Dataset for Group Action Quality Assessment
Action quality assessment (AQA) has become an emerging topic since it can be extensively applied in numerous scenarios.
Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategy
Recently, dynamic computation methods have shown notable acceleration for Large Language Models (LLMs) by skipping several layers of computations through elaborate heuristics or additional predictors.
Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective
In this paper, we suggest that code comments are the natural logic pivot between natural language and code language and propose using comments to boost the code generation ability of code LLMs.
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.
UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs
The rapid development of LLMs calls for a lightweight and easy-to-use framework for swift evaluation deployment.
P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting
Nowadays, pre-training big models on large-scale datasets has become a crucial topic in deep learning.
Ranked #16 on
3D Point Cloud Classification
on ScanObjectNN
(using extra training data)
Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding
This paper describes our solution for the video recognition task of the Google Cloud and YouTube-8M Video Understanding Challenge that ranked the 3rd place.
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
Based on this hypothesis, we propose to learn point cloud representation by bidirectional reasoning between the local structures at different abstraction hierarchies and the global shape without human supervision.
Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning
In-context learning (ICL) emerges as a promising capability of large language models (LLMs) by providing them with demonstration examples to perform diverse tasks.
Adaptive Graph Encoder for Attributed Graph Embedding
Experimental results show that AGE consistently outperforms state-of-the-art graph embedding methods considerably on these tasks.
Ranked #6 on
Node Clustering
on Cora
Learning from Context or Names? An Empirical Study on Neural Relation Extraction
We find that (i) while context is the main source to support the predictions, RE models also heavily rely on the information from entity mentions, most of which is type information, and (ii) existing datasets may leak shallow heuristics via entity mentions and thus contribute to the high performance on RE benchmarks.
Ranked #23 on
Relation Extraction
on TACRED
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.
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.
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.
Towards Robust k-Nearest-Neighbor Machine Translation
Meanwhile we inject two types of perturbations into the retrieved pairs for robust training.
PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction
To address this, we propose a cylindrical tri-perspective view to represent point clouds effectively and comprehensively and a PointOcc model to process them efficiently.
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.
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.
Incremental Transformer with Deliberation Decoder for Document Grounded Conversations
Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document.
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.
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 #4 on
Action Segmentation
on GTEA
(using extra training data)
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.
HMEAE: Hierarchical Modular Event Argument Extraction
Existing event extraction methods classify each argument role independently, ignoring the conceptual correlations between different argument roles.
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.
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 #16 on
Metric Learning
on CUB-200-2011
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
It has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models.
Ranked #2 on
Semantic Segmentation
on ADE20K
(using extra training data)
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.
3D Small Object Detection with Dynamic Spatial Pruning
Specifically, we theoretically derive a dynamic spatial pruning (DSP) strategy to prune the redundant spatial representation of 3D scene in a cascade manner according to the distribution of objects.
CLEVE: Contrastive Pre-training for Event Extraction
Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning.
Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models
In the realm of vision-language understanding, the proficiency of models in interpreting and reasoning over visual content has become a cornerstone for numerous applications.
Ranked #41 on
Visual Question Answering
on MM-Vet
Demystify Transformers & Convolutions in Modern Image Deep Networks
Our experiments on various tasks and an analysis of inductive bias show a significant performance boost due to advanced network-level and block-level designs, but performance differences persist among different STMs.
GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
Current state-of-the-art systems for sequence labeling are typically based on the family of Recurrent Neural Networks (RNNs).
Ranked #17 on
Named Entity Recognition (NER)
on CoNLL 2003 (English)
(using extra training data)
Fully Hyperbolic Neural Networks
Hyperbolic neural networks have shown great potential for modeling complex data.
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.
DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion
Unlike previous work that relies on carefully designed network architectures and loss functions to fuse the information from the source and target faces, we reformulate the face swapping as a conditional inpainting task, performed by a powerful diffusion model guided by the desired face attributes (e. g., identity and landmarks).
Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
While question answering (QA) with neural network, i. e. neural QA, has achieved promising results in recent years, lacking of large scale real-word QA dataset is still a challenge for developing and evaluating neural QA system.
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.
Attention Cube Network for Image Restoration
The adaptive spatial attention branch (ASAB) and the adaptive channel attention branch (ACAB) constitute the adaptive dual attention module (ADAM), which can capture the long-range spatial and channel-wise contextual information to expand the receptive field and distinguish different types of information for more effective feature representations.
MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction
It contains 103, 193 event coreference chains, 1, 216, 217 temporal relations, 57, 992 causal relations, and 15, 841 subevent relations, which is larger than existing datasets of all the ERE tasks by at least an order of magnitude.
PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds
In this paper, we propose a Point-Voxel Recurrent All-Pairs Field Transforms (PV-RAFT) method to estimate scene flow from point clouds.
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.
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 #2 on
Action Quality Assessment
on MTL-AQA
Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog
Audio-Visual Scene-Aware Dialog (AVSD) is a task to generate responses when chatting about a given video, which is organized as a track of the 8th Dialog System Technology Challenge (DSTC8).
MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory
Due to the high price and heavy energy consumption of GPUs, deploying deep models on IoT devices such as microcontrollers makes significant contributions for ecological AI.
HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extraction
Multi-scenario & multi-task learning has been widely applied to many recommendation systems in industrial applications, wherein an effective and practical approach is to carry out multi-scenario transfer learning on the basis of the Mixture-of-Expert (MoE) architecture.
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.
Plug-and-Play Knowledge Injection for Pre-trained Language Models
Experimental results on three knowledge-driven NLP tasks show that existing injection methods are not suitable for the new paradigm, while map-tuning effectively improves the performance of downstream models.
Cross-Modal Adapter for Text-Video Retrieval
However, as pre-trained models are scaling up, fully fine-tuning them on text-video retrieval datasets has a high risk of overfitting.
Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution
On the other hand, we propose a parallel network which includes two branches of cascaded lookup tables which process different components of the input low-resolution images.
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.
CSCD-IME: Correcting Spelling Errors Generated by Pinyin IME
In fact, most of Chinese input is based on pinyin input method, so the study of spelling errors in this process is more practical and valuable.
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 #21 on
Person Re-Identification
on MSMT17
Towards Fine-grained Text Sentiment Transfer
In this paper, we focus on the task of fine-grained text sentiment transfer (FGST).
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.
A Simple Baseline for Multi-Camera 3D Object Detection
First, we extract multi-scale features and generate the perspective object proposals on each monocular image.
SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
Conventional point cloud semantic segmentation methods usually employ an encoder-decoder architecture, where mid-level features are locally aggregated to extract geometric information.
Introspective Deep Metric Learning for Image Retrieval
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images.
Introspective Deep Metric Learning
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images.
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.
Dynamic Context-guided Capsule Network for Multimodal Machine Translation
Particularly, we represent the input image with global and regional visual features, we introduce two parallel DCCNs to model multimodal context vectors with visual features at different granularities.
Ranked #3 on
Multimodal Machine Translation
on Multi30K
Deep Relational Metric Learning
This paper presents a deep relational metric learning (DRML) framework for image clustering and retrieval.
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.
Is ChatGPT a Good NLG Evaluator? A Preliminary Study
In detail, we regard ChatGPT as a human evaluator and give task-specific (e. g., summarization) and aspect-specific (e. g., relevance) instruction to prompt ChatGPT to evaluate the generated results of NLG models.
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.
Dynamic Knowledge Distillation for Pre-trained Language Models
Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models.
Uncertainty-aware Score Distribution Learning for Action Quality Assessment
Assessing action quality from videos has attracted growing attention in recent years.
Ranked #4 on
Action Quality Assessment
on AQA-7
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.
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).
TIM: Teaching Large Language Models to Translate with Comparison
Open-sourced large language models (LLMs) have demonstrated remarkable efficacy in various tasks with instruction 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.
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.
Ranked #3 on
Causal Emotion Entailment
on RECCON
Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA
To overcome this limitation, we propose a new dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.
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.
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.
AKConv: Convolutional Kernel with Arbitrary Sampled Shapes and Arbitrary Number of Parameters
In response to the above questions, the Alterable Kernel Convolution (AKConv) is explored in this work, which gives the convolution kernel an arbitrary number of parameters and arbitrary sampled shapes to provide richer options for the trade-off between network overhead and performance.
Attributable Visual Similarity Learning
This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and explainable similarity measure between images.
Ranked #3 on
Metric Learning
on CARS196
(using extra training data)
NumNet: Machine Reading Comprehension with Numerical Reasoning
Numerical reasoning, such as addition, subtraction, sorting and counting is a critical skill in human's reading comprehension, which has not been well considered in existing machine reading comprehension (MRC) systems.
Ranked #10 on
Question Answering
on DROP Test
Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes
In this article, we propose Human-M3, an outdoor multi-modal multi-view multi-person human pose database which includes not only multi-view RGB videos of outdoor scenes but also corresponding pointclouds.
CokeBERT: Contextual Knowledge Selection and Embedding towards Enhanced Pre-Trained Language Models
In this paper, we propose a novel framework named Coke to dynamically select contextual knowledge and embed knowledge context according to textual context for PLMs, which can avoid the effect of redundant and ambiguous knowledge in KGs that cannot match the input text.
Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
An ordinal distribution constraint is proposed to exploit the ordinal nature of regression.
Ranked #2 on
Age Estimation
on Adience
Aesthetics Quality Assessment
Age And Gender Classification
+3
ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization
We present ClidSum, a benchmark dataset for building cross-lingual summarization systems on dialogue documents.
Siamese Image Modeling for Self-Supervised Vision Representation Learning
Driven by these analysis, we propose Siamese Image Modeling (SiameseIM), which predicts the dense representations of an augmented view, based on another masked view from the same image but with different augmentations.
OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions
The pretrain-finetune paradigm in modern computer vision facilitates the success of self-supervised learning, which tends to achieve better transferability than supervised learning.
A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation
Multi-modal neural machine translation (NMT) aims to translate source sentences into a target language paired with images.
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.
CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation
Existing reference-free metrics have obvious limitations for evaluating controlled text generation models.
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models
In this paper, we propose a novel 3D-to-2D generative pre-training method that is adaptable to any point cloud model.
Ranked #6 on
3D Part Segmentation
on ShapeNet-Part
ELLE: Efficient Lifelong Pre-training for Emerging Data
We experiment ELLE with streaming data from 5 domains on BERT and GPT.
OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression
In this paper, we propose to learn the rank concepts from the rich semantic CLIP latent space.
Ranked #1 on
Few-shot Age Estimation
on MORPH Album2
SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis
However, due to the variety of users{'} emotional expressions across domains, fine-tuning the pre-trained models on the source domain tends to overfit, leading to inferior results on the target domain.
CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding
Spoken Language Understanding (SLU) mainly involves two tasks, intent detection and slot filling, which are generally modeled jointly in existing works.
Ranked #1 on
Slot Filling
on CAIS
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.
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.
Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection
We use a fine-grained encoding strategy which is more sensitive to the emotion dynamics (emotion flow) in the conversations to predict the emotion-intent characteristic of response.
Mixture of Attention Heads: Selecting Attention Heads Per Token
This paper proposes the Mixture of Attention Heads (MoA), a new architecture that combines multi-head attention with the MoE mechanism.
Feature Decomposition for Reducing Negative Transfer: A Novel Multi-task Learning Method for Recommender System
In recent years, thanks to the rapid development of deep learning (DL), DL-based multi-task learning (MTL) has made significant progress, and it has been successfully applied to recommendation systems (RS).
LiDAR-based Person Re-identification
Camera-based person re-identification (ReID) systems have been widely applied in the field of public security.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
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.
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.
Ranked #1 on
Causal Emotion Entailment
on RECCON
Label2Label: A Language Modeling Framework for Multi-Attribute Learning
As each sample is annotated with multiple attribute labels, these "words" will naturally form an unordered but meaningful "sentence", which depicts the semantic information of the corresponding sample.
On Prompt-Driven Safeguarding for Large Language Models
Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) from complying with queries that contain harmful intents.
DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog
Visual Dialog is a vision-language task that requires an AI agent to engage in a conversation with humans grounded in an image.
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.
Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models
Prompting, which casts downstream applications as language modeling tasks, has shown to be sample efficient compared to standard fine-tuning with pre-trained models.
Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation
Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information.
Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation
Non-Autoregressive Neural Machine Translation (NAT) achieves significant decoding speedup through generating target words independently and simultaneously.
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.
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.
Transformer-Patcher: One Mistake worth One Neuron
Our method outperforms previous fine-tuning and HyperNetwork-based methods and achieves state-of-the-art performance for Sequential Model Editing (SME).
Efficient Meshy Neural Fields for Animatable Human Avatars
Moreover, only minutes of optimization is enough for plausible reconstruction results.
A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis
Aspect based sentiment analysis (ABSA) aims to identify the sentiment polarity towards the given aspect in a sentence, while previous models typically exploit an aspect-independent (weakly associative) encoder for sentence representation generation.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and Explanation
As a result, this model performs quite well in both validation and explanation.
Evaluating Modules in Graph Contrastive Learning
The recent emergence of contrastive learning approaches facilitates the application on graph representation learning (GRL), introducing graph contrastive learning (GCL) into the literature.
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 #20 on
Semantic Segmentation
on ScanNet
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.
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.
Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search
Differentiable architecture search (DARTS) acquires the optimal architectures by optimizing the architecture parameters with gradient descent, which significantly reduces the search cost.
A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models
In response to the efficiency problem, recent studies show that dense PLMs can be replaced with sparse subnetworks without hurting the performance.
Token-Label Alignment for Vision Transformers
Data mixing strategies (e. g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs).
Instruction Position Matters in Sequence Generation with Large Language Models
Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning.
Token-level Adaptive Training for Neural Machine Translation
The vanilla NMT model usually adopts trivial equal-weighted objectives for target tokens with different frequencies and tends to generate more high-frequency tokens and less low-frequency tokens compared with the golden token distribution.
Towards Codable Watermarking for Injecting Multi-bits Information to LLMs
As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs.
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.
Deep Compositional Metric Learning
In this paper, we propose a deep compositional metric learning (DCML) framework for effective and generalizable similarity measurement between images.
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.
From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models
We then design a Model Uncertainty--aware Knowledge Integration (MUKI) framework to recover the golden supervision for the student.
Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation
By dynamically determining segment length and deleting repetitive segments, RecoverSAT is capable of recovering from repetitive and missing token errors.
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.
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).
Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation
We propose a novel model to separate the generation into two stages: key fact prediction and surface realization.
SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor
Besides local features, global information plays an essential role in semantic segmentation, while recent works usually fail to explicitly extract the meaningful global information and make full use of it.
Graph-Based Social Relation Reasoning
Human beings are fundamentally sociable -- that we generally organize our social lives in terms of relations with other people.
Ranked #1 on
Visual Social Relationship Recognition
on PIPA
Large Language Models Are Not Robust Multiple Choice Selectors
This work shows that modern LLMs are vulnerable to option position changes in MCQs due to their inherent "selection bias", namely, they prefer to select specific option IDs as answers (like "Option A").
An Improved Evaluation Framework for Generative Adversarial Networks
Unlike most existing evaluation frameworks which transfer the representation of ImageNet inception model to map images onto the feature space, our framework uses a specialized encoder to acquire fine-grained domain-specific representation.
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.
Deep Factorized Metric Learning
Learning a generalizable and comprehensive similarity metric to depict the semantic discrepancies between images is the foundation of many computer vision tasks.
Emergent Modularity in Pre-trained Transformers
In analogy to human brains, we consider two main characteristics of modularity: (1) functional specialization of neurons: we evaluate whether each neuron is mainly specialized in a certain function, and find that the answer is yes.
LiDAR-HMR: 3D Human Mesh Recovery from LiDAR
In recent years, point cloud perception tasks have been garnering increasing attention.
Ranked #1 on
3D Human Pose Estimation
on SLOPER4D
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).
Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment
Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing.
Let's Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models
Aspect-Based Sentiment Analysis (ABSA) stands as a crucial task in predicting the sentiment polarity associated with identified aspects within text.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion
Based on the datasets, we propose novel tasks such as multi-hop knowledge abstraction (MKA), multi-hop knowledge concretization (MKC) and then design a comprehensive benchmark.
Structure-Enhanced Pop Music Generation via Harmony-Aware Learning
Experimental results reveal that compared to the existing methods, HAT owns a much better understanding of the structure and it can also improve the quality of generated music, especially in the form and texture.
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.
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.
Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents
Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions.
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
We first formulate a general framework of agent backdoor attacks, then we present a thorough analysis on the different forms of agent backdoor attacks.
Robust Facial Landmark Detection by Multi-order Multi-constraint Deep Networks
Recently, heatmap regression has been widely explored in facial landmark detection and obtained remarkable performance.
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.
