Search Results for author:
Found 42 papers, 20 papers with code
DragAnything: Motion Control for Anything using Entity Representation
We introduce DragAnything, which utilizes a entity representation to achieve motion control for any object in controllable video generation.
SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting
We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh, which renders over 300 FPS on a modern GPU and 30 FPS on a mobile device.
AugNet: End-to-End Unsupervised Visual Representation Learning with Image Augmentation
In our evaluations, the method outperforms all the state-of-the-art image retrieval algorithms on some out-of-domain image datasets.
Paragraph-to-Image Generation with Information-Enriched Diffusion Model
In this paper, we introduce an information-enriched diffusion model for paragraph-to-image generation task, termed ParaDiffusion, which delves into the transference of the extensive semantic comprehension capabilities of large language models to the task of image generation.
FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing
Textual scene graph parsing has become increasingly important in various vision-language applications, including image caption evaluation and image retrieval.
Ranked #2 on
Human Judgment Correlation
on Flickr8k-Expert
A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data.
Context Dependent Semantic Parsing: A Survey
Semantic parsing is the task of translating natural language utterances into machine-readable meaning representations.
A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension
Most existing cross-modal language-to-video retrieval (VR) research focuses on single-modal input from video, i. e., visual representation, while the text is omnipresent in human environments and frequently critical to understand video.
SocialDial: A Benchmark for Socially-Aware Dialogue Systems
To the best of our knowledge, SocialDial is the first socially-aware dialogue dataset that covers multiple social factors and has fine-grained labels.
Cultural Vocal Bursts Intensity Prediction
Synthetic Data Generation
FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation
This paper introduces a novel video text synthesis technique called FlowText, which utilizes optical flow estimation to synthesize a large amount of text video data at a low cost for training robust video text spotters.
Continual Learning for Image Segmentation with Dynamic Query
Image segmentation based on continual learning exhibits a critical drop of performance, mainly due to catastrophic forgetting and background shift, as they are required to incorporate new classes continually.
Strong Instance Segmentation Pipeline for MMSports Challenge
The goal of ACM MMSports2022 DeepSportRadar Instance Segmentation Challenge is to tackle the segmentation of individual humans including players, coaches and referees on a basketball court.
Few-Shot Semantic Parsing for New Predicates
In this work, we investigate the problems of semantic parsing in a few-shot learning setting.
Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers
We conduct extensive experiments to study the research problems involved in continual semantic parsing and demonstrate that a neural semantic parser trained with TotalRecall achieves superior performance than the one trained directly with the SOTA continual learning algorithms and achieve a 3-6 times speedup compared to re-training from scratch.
Contrastive Learning of Semantic and Visual Representations for Text Tracking
Semantic representation is of great benefit to the video text tracking(VTT) task that requires simultaneously classifying, detecting, and tracking texts in the video.
Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e. g., text detection, tracking, recognition) in a real-time end-to-end trainable framework.
Compositional Generalization for Multi-label Text Classification: A Data-Augmentation Approach
Our experiments show that this data augmentation approach significantly improves the compositional generalization capabilities of classification models on our benchmarks, with both generation models surpassing other text generation baselines.
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation
In this paper, we propose a variational autoencoder with disentanglement priors, VAE-DPRIOR, for task-specific natural language generation with none or a handful of task-specific labeled examples.
TMID: A Comprehensive Real-world Dataset for Trademark Infringement Detection in E-Commerce
Annually, e-commerce platforms incur substantial financial losses due to trademark infringements, making it crucial to identify and mitigate potential legal risks tied to merchant information registered to the platforms.
Asymmetric Correntropy for Robust Adaptive Filtering
Correntropy is generally defined as the expectation of a Gaussian kernel between two random variables.
On Robustness of Neural Semantic Parsers
In this paper, we provide the empirical study on the robustness of semantic parsers in the presence of adversarial attacks.
Representation Learning for Weakly Supervised Relation Extraction
The experiments have demonstrated that this type of feature, combine with the traditional hand-crafted features, could improve the performance of the logistic classification model for relation extraction, especially on the classification of relations with only minor training instances.
Pretrained Language Model in Continual Learning: A Comparative Study
In this paper, we thoroughly compare the continual learning performance over the combination of 5 PLMs and 4 veins of CL methods on 3 benchmarks in 2 typical incremental settings.
Paraphrasing Techniques for Maritime QA system
In this paper, we investigate how to exploit paraphrasing methods for the automated generation of large-scale training datasets (in the form of paraphrased utterances and their corresponding logical forms in SQL format) and present our experimental results using real-world data in the maritime domain.
A Zipf's Law-based Text Generation Approach for Addressing Imbalance in Entity Extraction
The Zipf's Law emerges as a well-suited adoption, and to transition from words to entities, words within the documents are classified as common and rare ones.
The Second Place Solution for The 4th Large-scale Video Object Segmentation Challenge--Track 3: Referring Video Object Segmentation
The referring video object segmentation task (RVOS) aims to segment object instances in a given video referred by a language expression in all video frames.
The Third Place Solution for CVPR2022 AVA Accessibility Vision and Autonomy Challenge
Finally, our approach achieves 63. 008\%AP@0. 50:0. 95 on the test set of CVPR2022 AVA Challenge.
Let's Negotiate! A Survey of Negotiation Dialogue Systems
Negotiation is one of the crucial abilities in human communication, and there has been a resurgent research interest in negotiation dialogue systems recently, which goal is to empower intelligent agents with such ability that can efficiently help humans resolve conflicts or reach beneficial agreements.
Active Learning for Multilingual Semantic Parser
Current multilingual semantic parsing (MSP) datasets are almost all collected by translating the utterances in the existing datasets from the resource-rich language to the target language.
On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex
Semantic parsing is a technique aimed at constructing a structured representation of the meaning of a natural-language question.
ICDAR 2023 Video Text Reading Competition for Dense and Small Text
In this competition report, we establish a video text reading benchmark, DSText, which focuses on dense and small text reading challenges in the video with various scenarios.
The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning
Multilingual semantic parsing aims to leverage the knowledge from the high-resource languages to improve low-resource semantic parsing, yet commonly suffers from the data imbalance problem.
Semantic Parsing in Limited Resource Conditions
This thesis explores challenges in semantic parsing, specifically focusing on scenarios with limited data and computational resources.
Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models
Our approach involves initially generating a set of candidate outputs by prompting an LLM and subsequently reranking them using a task-specific reranker model.
Natural Language Processing for Dialects of a Language: A Survey
Motivated by the performance degradation of NLP models for dialectic datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches.
Let's Negotiate! A Survey of Negotiation Dialogue Systems
Negotiation is a crucial ability in human communication.
SADAS: A Dialogue Assistant System Towards Remediating Norm Violations in Bilingual Socio-Cultural Conversations
We have released our code and software at:~\url{https://github. com/AnonymousEACLDemo/SADAS}.
Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach
Post-editing has proven effective in improving the quality of text generated by large language models (LLMs) such as GPT-3. 5 or GPT-4, particularly when direct updating of their parameters to enhance text quality is infeasible or expensive.
RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversations
While collecting sufficient human-authored data is costly, synthetic conversations provide suitable amounts of data to help mitigate the scarcity of training data, as well as the chance to assess the alignment between LLMs and humans in the awareness of social norms.
StarCoder 2 and The Stack v2: The Next Generation
Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size.
Ranked #24 on
Code Generation
on MBPP
Towards Detecting AI-Generated Text within Human-AI Collaborative Hybrid Texts
Our empirical findings highlight (1) detecting AI-generated sentences in hybrid texts is overall a challenging task because (1. 1) human writers' selecting and even editing AI-generated sentences based on personal preferences adds difficulty in identifying the authorship of segments; (1. 2) the frequent change of authorship between neighboring sentences within the hybrid text creates difficulties for segment detectors in identifying authorship-consistent segments; (1. 3) the short length of text segments within hybrid texts provides limited stylistic cues for reliable authorship determination; (2) before embarking on the detection process, it is beneficial to assess the average length of segments within the hybrid text.
