Search Results for author:
Found 38 papers, 23 papers with code
RFUAV: A Benchmark Dataset for Unmanned Aerial Vehicle Detection and Identification
In addition to the dataset, RFUAV provides a baseline preprocessing method and model evaluation tools.
Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent
Aligned with professional human interpreters, we evaluate CLASI with a better human evaluation metric, valid information proportion (VIP), which measures the amount of information that can be successfully conveyed to the listeners.
NTIRE 2024 Challenge on Night Photography Rendering
The top ranking participants' solutions effectively represent the state-of-the-art in nighttime photography rendering.
Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model
However, a large portion of videos in real-world applications are edited videos, \textit{e. g.}, users usually cut and add effects/modifications to the raw video before publishing it on social media platforms.
Sparsity- and Hybridity-Inspired Visual Parameter-Efficient Fine-Tuning for Medical Diagnosis
The success of Large Vision Models (LVMs) is accompanied by vast data volumes, which are prohibitively expensive in medical diagnosis. To address this, recent efforts exploit Parameter-Efficient Fine-Tuning (PEFT), which trains a small number of weights while freezing the rest. However, they typically assign trainable weights to the same positions in LVMs in a heuristic manner, regardless of task differences, making them suboptimal for professional applications like medical diagnosis. To address this, we statistically reveal the nature of sparsity and hybridity during diagnostic-targeted fine-tuning, i. e., a small portion of key weights significantly impacts performance, and these key weights are hybrid, including both task-specific and task-agnostic parts. Based on this, we propose a novel Sparsity- and Hybridity-inspired Parameter Efficient Fine-Tuning (SH-PEFT). It selects and trains a small portion of weights based on their importance, which is innovatively estimated by hybridizing both task-specific and task-agnostic strategies. Validated on six medical datasets of different modalities, we demonstrate that SH-PEFT achieves state-of-the-art performance in transferring LVMs to medical diagnosis in terms of accuracy.
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
Recent advancements in Multimodal Large Language Models (LLMs) have focused primarily on scaling by increasing text-image pair data and enhancing LLMs to improve performance on multimodal tasks.
Ranked #1 on
visual instruction following
on LLaVA-Bench
End-to-end training of Multimodal Model and ranking Model
In this paper, we propose an industrial multimodal recommendation framework named EM3: End-to-end training of Multimodal Model and ranking Model, which sufficiently utilizes multimodal information and allows personalized ranking tasks to directly train the core modules in the multimodal model to obtain more task-oriented content features, without overburdening resource consumption.
HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting
Holistic understanding of urban scenes based on RGB images is a challenging yet important problem.
PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models
Large Language Models (LLMs) have succeeded remarkably in understanding long-form contents.
Parameter-Efficient Conversational Recommender System as a Language Processing Task
Conversational recommender systems (CRS) aim to recommend relevant items to users by eliciting user preference through natural language conversation.
The Memory Perturbation Equation: Understanding Model's Sensitivity to Data
Understanding model's sensitivity to its training data is crucial but can also be challenging and costly, especially during training.
Decomposed Prompt Tuning via Low-Rank Reparameterization
While prompt tuning approaches have achieved competitive performance with high efficiency, we observe that they invariably employ the same initialization process, wherein the soft prompt is either randomly initialized or derived from an existing embedding vocabulary.
Informative Scene Graph Generation via Debiasing
It integrates two components: Semantic Debiasing (SD) and Balanced Predicate Learning (BPL), for these imbalances.
Learning Large Margin Sparse Embeddings for Open Set Medical Diagnosis
To tackle OSR, we assume that known classes could densely occupy small parts of the embedding space and the remaining sparse regions could be recognized as unknowns.
Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data
We conducted experiments on document-level and biomedical relation extraction datasets, and the results showed that our proposed self-training framework consistently outperforms existing competitive methods on the Re-DocRED and ChemDisgene datasets when the training data are incompletely annotated.
Better Sampling of Negatives for Distantly Supervised Named Entity Recognition
Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data instead of human annotations.
Feature-Aligned Video Raindrop Removal with Temporal Constraints
Our single image module employs a raindrop removal network to generate initial raindrop removal results, and create a mask representing the differences between the input and initial output.
Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction
We analyze the causes and effects of the overwhelming false negative problem in the DocRED dataset.
Parallel Network with Channel Attention and Post-Processing for Carotid Arteries Vulnerable Plaque Segmentation in Ultrasound Images
Test results show that the proposed method with dice loss function yields a Dice value of 0. 820, an IoU of 0. 701, Acc of 0. 969, and modified Hausdorff distance (MHD) of 1. 43 for 30 vulnerable cases of plaques, it outperforms some of the conventional CNN-based methods on these metrics.
Document-level Relation Extraction with Context Guided Mention Integration and Inter-pair Reasoning
Document-level Relation Extraction (DRE) aims to recognize the relations between two entities.
Ranked #5 on
Relation Extraction
on CDR
SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based Sentiment Analysis
We inject sentiment knowledge regarding aspects, opinions, and polarities into prompt and explicitly model term relations via constructing consistency and polarity judgment templates from the ground truth triplets.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+5
Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction
Aspect Sentiment Triplet Extraction (ASTE) is the most recent subtask of ABSA which outputs triplets of an aspect target, its associated sentiment, and the corresponding opinion term.
Ranked #3 on
Aspect Sentiment Triplet Extraction
on MuseASTE
Aspect-Based Sentiment Analysis (ABSA)
Aspect Sentiment Triplet Extraction
+3
A CNN Segmentation-Based Approach to Object Detection and Tracking in Ultrasound Scans with Application to the Vagus Nerve Detection
Real-time accurate and robust automatic detection and tracking of anatomical structures while scanning would significantly impact diagnostic and therapeutic procedures to be consistent and efficient.
Low-Dose CT Denoising Using a Structure-Preserving Kernel Prediction Network
Low-dose CT has been a key diagnostic imaging modality to reduce the potential risk of radiation overdose to patient health.
Better Feature Integration for Named Entity Recognition
We believe this is because both types of features - the contextual information captured by the linear sequences and the structured information captured by the dependency trees may complement each other.
Quasi-static limit for a hyperbolic conservation law
We study the quasi-static limit for the $L^\infty$ entropy weak solution of scalar one-dimensional hyperbolic equations with strictly concave or convex flux and time dependent boundary conditions.
Analysis of PDEs 35D40, 35I04
Efficient Deep Image Denoising via Class Specific Convolution
In this paper, we propose an efficient deep neural network for image denoising based on pixel-wise classification.
A new volatility model: GQARCH-Itô model
Volatility asymmetry is a hot topic in high-frequency financial market.
Methodology
ComboLoss for Facial Attractiveness Analysis with Squeeze-and-Excitation Networks
Loss function is crucial for model training and feature representation learning, conventional models usually regard facial attractiveness recognition task as a regression problem, and adopt MSE loss or Huber variant loss as supervision to train a deep convolutional neural network (CNN) to predict facial attractiveness score.
Multimedia
Position-Aware Tagging for Aspect Sentiment Triplet Extraction
Our observation is that the three elements within a triplet are highly related to each other, and this motivates us to build a joint model to extract such triplets using a sequence tagging approach.
Ranked #3 on
Aspect Sentiment Triplet Extraction
on SemEval
Aspect Based Sentiment Analysis with Aspect-Specific Opinion Spans
Such a design allows the model to extract aspect-specific opinion spans and then evaluate sentiment polarity by exploiting the extracted opinion features.
Emergence of Pragmatics from Referential Game between Theory of Mind Agents
Pragmatics studies how context can contribute to language meanings.
XCloud: Design and Implementation of AI Cloud Platform with RESTful API Service
In recent years, artificial intelligence (AI) has aroused much attention among both industrial and academic areas.
Distributed, Parallel, and Cluster Computing
Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis
In this paper, we introduce a new subtask under ABSA, named aspect sentiment triplet extraction (ASTE).
Ranked #5 on
Aspect Sentiment Triplet Extraction
on SemEval
Data-driven Approach for Quality Evaluation on Knowledge Sharing Platform
In recent years, voice knowledge sharing and question answering (Q&A) platforms have attracted much attention, which greatly facilitate the knowledge acquisition for people.
Transferring Rich Deep Features for Facial Beauty Prediction
Feature extraction plays a significant part in computer vision tasks.
Ranked #1 on
Facial Beauty Prediction
on SCUT-FBP
Computer-aided implant design for the restoration of cranial defects
Patient-specific cranial implants are important and necessary in the surgery of cranial defect restoration.
A semi-automatic computer-aided method for surgical template design
Then, the offset surface of the inner surface is obtained through contouring the distance field of the inner surface, and segmented to generate the outer surface.
