Search Results for author:
Found 51 papers, 17 papers with code
Continuing Pre-trained Model with Multiple Training Strategies for Emotional Classification
This paper describes the contribution of the LingJing team’s method to the Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA) 2022 shared task on Emotion Classification.
LingJing at SemEval-2022 Task 3: Applying DeBERTa to Lexical-level Presupposed Relation Taxonomy with Knowledge Transfer
For the classification sub-task, we adopt the DeBERTa-v3 pre-trained model for fine-tuning datasets of different languages.
LingJing at SemEval-2022 Task 1: Multi-task Self-supervised Pre-training for Multilingual Reverse Dictionary
This paper introduces the approach of Team LingJing’s experiments on SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings (CODWOE).
VPAI_Lab at MedVidQA 2022: A Two-Stage Cross-modal Fusion Method for Medical Instructional Video Classification
Given an input video, the MedVidCL task aims to correctly classify it into one of three following categories: Medical Instructional, Medical Non-instructional, and Non-medical.
Do Multimodal Language Models Really Understand Direction? A Benchmark for Compass Direction Reasoning
Direction reasoning is essential for intelligent systems to understand the real world.
DrVideo: Document Retrieval Based Long Video Understanding
Specifically, DrVideo first transforms a long video into a coarse text-based long document to initially retrieve key frames and then updates the documents with the augmented key frame information.
Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation
In DDS, both sequence-level and token-level adaptive search can be achieved to adjust the decoding process in a unified framework.
GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering
Therefore, we propose GeReA, a generate-reason framework that prompts a MLLM like InstructBLIP with question relevant vision and language information to generate knowledge-relevant descriptions and reasons those descriptions for knowledge-based VQA.
Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data
In this work, we illustrate the merit of negative data and propose a model specialization framework to distill LLMs with negative samples besides positive ones.
EXMODD: An EXplanatory Multimodal Open-Domain Dialogue dataset
The need for high-quality data has been a key issue hindering the research of dialogue tasks.
Large Language Models Need Holistically Thought in Medical Conversational QA
The medical conversational question answering (CQA) system aims at providing a series of professional medical services to improve the efficiency of medical care.
LOGO-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition
Previous methods for dynamic facial expression recognition (DFER) in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos.
Dynamic Facial Expression Recognition
Facial Expression Recognition
Heterogeneous-Branch Collaborative Learning for Dialogue Generation
Collaborative learning, also known as online knowledge distillation, is an effective way to conduct one-stage group distillation in the absence of a well-trained large teacher model.
Image as Set of Points
Context clusters (CoCs) view an image as a set of unorganized points and extract features via simplified clustering algorithm.
Large Language Models are Better Reasoners with Self-Verification
By performing a backward verification of the answers that LLM deduced for itself, we can obtain interpretable answer validation scores to select the candidate answer with the highest score.
Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables
Specifically, HLV constrains the global semantics of responses through discrete latent variables and enriches responses with continuous latent variables.
Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder
Complex dialogue mappings (CDM), including one-to-many and many-to-one mappings, tend to make dialogue models generate incoherent or dull responses, and modeling these mappings remains a huge challenge for neural dialogue systems.
Learning to Locate Visual Answer in Video Corpus Using Question
We introduce a new task, named video corpus visual answer localization (VCVAL), which aims to locate the visual answer in a large collection of untrimmed instructional videos using a natural language question.
TransFiner: A Full-Scale Refinement Approach for Multiple Object Tracking
Multiple object tracking (MOT) is the task containing detection and association.
Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation
To fully leverage the visual information for both scene understanding and dialogue generation, we propose the scene-aware prompt for the MDUG task.
Explicit and implicit models in infrared and visible image fusion
Infrared and visible images, as multi-modal image pairs, show significant differences in the expression of the same scene.
Towards Layer-wise Image Vectorization
Image rasterization is a mature technique in computer graphics, while image vectorization, the reverse path of rasterization, remains a major challenge.
Stop Filtering: Multi-View Attribute-Enhanced Dialogue Learning
However, the discarded samples may obtain high scores in other perspectives and can provide regularization effects on the model learning, which causes the performance improvement to be sensitive to the filtering ratio.
Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild
Previous methods for dynamic facial expression in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos.
Ranked #10 on
Dynamic Facial Expression Recognition
on FERV39k
Dynamic Facial Expression Recognition
Facial Expression Recognition
+1
Diversifying Neural Dialogue Generation via Negative Distillation
Generative dialogue models suffer badly from the generic response problem, limiting their applications to a few toy scenarios.
LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs
The medical conversational system can relieve the burden of doctors and improve the efficiency of healthcare, especially during the pandemic.
Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution
In this paper, we propose a novel Hybrid Pixel-Unshuffled Network (HPUN) by introducing an efficient and effective downsampling module into the SR task.
Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video
However, due to the weak correlations and huge gaps of the semantic features between the textual question and visual answer, existing methods adopting visual span predictor perform poorly in the TAGV task.
SimCLAD: A Simple Framework for Contrastive Learning of Acronym Disambiguation
In this paper, we propose a Simple framework for Contrastive Learning of Acronym Disambiguation (SimCLAD) method to better understand the acronym meanings.
PSG: Prompt-based Sequence Generation for Acronym Extraction
In this paper, we propose a Prompt-based Sequence Generation (PSG) method for the acronym extraction task.
Hybrid Mutimodal Fusion for Dimensional Emotion Recognition
For the MuSe-Stress sub-challenge, we highlight our solutions in three aspects: 1) the audio-visual features and the bio-signal features are used for emotional state recognition.
Sign Language Recognition via Skeleton-Aware Multi-Model Ensemble
Current Sign Language Recognition (SLR) methods usually extract features via deep neural networks and suffer overfitting due to limited and noisy data.
Grassmannian Graph-attentional Landmark Selection for Domain Adaptation
GGLS presents a landmark selection scheme using attention-induced neighbors of the graphical structure of samples and performs distribution adaptation and knowledge adaptation over Grassmann manifold.
More but Correct: Generating Diversified and Entity-revised Medical Response
Medical Dialogue Generation (MDG) is intended to build a medical dialogue system for intelligent consultation, which can communicate with patients in real-time, thereby improving the efficiency of clinical diagnosis with broad application prospects.
Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders
Conditional Variational AutoEncoder (CVAE) effectively increases the diversity and informativeness of responses in open-ended dialogue generation tasks through enriching the context vector with sampled latent variables.
THINK: A Novel Conversation Model for Generating Grammatically Correct and Coherent Responses
In this work, we proposed a conversation model named "THINK" (Teamwork generation Hover around Impressive Noticeable Keywords) to make the decoder more complicated and avoid generating duplicated and self-contradicting responses.
GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition
In the sampling stage, we utilize a generative adversarial networks (GAN) trained by action features and word vectors of seen classes to synthesize the action features of unseen classes, which can balance the training sample data of seen classes and unseen classes.
Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model
To tackle all these problems, we propose a real-time 3D action recognition framework by integrating the locally aggregated kinematic-guided skeletonlet (LAKS) with a supervised hashing-by-analysis (SHA) model.
Facial Expression Recognition with Visual Transformers and Attentional Selective Fusion
Facial Expression Recognition (FER) in the wild is extremely challenging due to occlusions, variant head poses, face deformation and motion blur under unconstrained conditions.
Facial Expression Recognition
Facial Expression Recognition (FER)
Skeleton Aware Multi-modal Sign Language Recognition
Sign language is commonly used by deaf or speech impaired people to communicate but requires significant effort to master.
Ranked #2 on
Sign Language Recognition
on AUTSL
(using extra training data)
Regularizing Dialogue Generation by Imitating Implicit Scenarios
Human dialogues are scenario-based and appropriate responses generally relate to the latent context knowledge entailed by the specific scenario.
Recent Advances and New Guidelines on Hyperspectral and Multispectral Image Fusion
Hyperspectral image (HSI) with high spectral resolution often suffers from low spatial resolution owing to the limitations of imaging sensors.
Fully Automated Multi-Organ Segmentation in Abdominal Magnetic Resonance Imaging with Deep Neural Networks
The model takes in multi-slice MR images and generates the output of segmentation results.
FollowMeUp Sports: New Benchmark for 2D Human Keypoint Recognition
Human pose estimation has made significant advancement in recent years.
Real-time Memory Efficient Large-pose Face Alignment via Deep Evolutionary Network
To accelerate the model, we propose an efficient network structure to accelerate the evolutionary learning process through a factorization strategy.
LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual Convolution
To reduce the computation and memory costs, we propose a novel lightweight deep learning module by low-rank pointwise residual (LPR) convolution, called LPRNet.
Cohomology of group theoretic Dehn fillings II
We apply these results to obtain hyperbolic and acylindrically hyperbolic quotients with special properties.
Group Theory 20F67, 20F10, 20E06
Cohomology of group theoretic Dehn fillings II: A spectral sequence
This is the second paper in a series of three papers aiming to study cohomology of group theoretic Dehn fillings.
Group Theory
EV-Action: Electromyography-Vision Multi-Modal Action Dataset
To make up this, we introduce a new, large-scale EV-Action dataset in this work, which consists of RGB, depth, electromyography (EMG), and two skeleton modalities.
Ranked #4 on
Multimodal Activity Recognition
on EV-Action
GeoCapsNet: Aerial to Ground view Image Geo-localization using Capsule Network
The task of cross-view image geo-localization aims to determine the geo-location (GPS coordinates) of a query ground-view image by matching it with the GPS-tagged aerial (satellite) images in a reference dataset.
