Computer Science - Multimedia

MultimediaCap2Sum: A New Approach to Video Summarization

Cap2Sum uses dense video captions to improve video summarization efficiency and effectiveness.

Cairong Zhao, Chutian Wang, Zifan Song

2025-06-23T23:55:42+00:00 ― 7 min read

Computation and LanguageIntroducing MaVEn: A New Approach to Multi-Image Understanding

MaVEn enhances AI's ability to process multiple images for better reasoning.

Chaoya Jiang, Jia Hongrui, Haiyang Xu

2025-06-23T15:38:00+00:00 ― 5 min read

SoundArtificial Intelligence and the Future of Music Creation

AI is reshaping how music is composed and experienced.

Sangjun Han, Jiwon Ham, Chaeeun Lee

2025-06-23T08:10:55+00:00 ― 6 min read

MultimediaBalancing Emotions: A New Approach in ERC

A new method improves emotion recognition in conversations using multiple data sources.

Cam-Van Thi Nguyen, The-Son Le, Anh-Tuan Mai

2025-06-23T01:01:06+00:00 ― 5 min read

Computer Vision and Pattern RecognitionNew Method for Text-3D Retrieval Using RMARN

Introducing RMARN: an innovative approach to connect text and 3D data.

Wenrui Li, Wei Han, Yandu Chen

2025-06-22T22:23:06+00:00 ― 5 min read

Computer Vision and Pattern RecognitionSceneDreamer360: Advancing 3D Scene Creation from Text

A new method transforms text into detailed 3D scenes seamlessly.

Wenrui Li, Fucheng Cai, Yapeng Mi

2025-06-22T22:15:12+00:00 ― 6 min read

Computer Vision and Pattern RecognitionCreating an Open Metaverse for All

A new approach to building accessible virtual spaces using WebXR and A-Frame.

Giuseppe Macario

2025-06-22T18:26:06+00:00 ― 6 min read

Computer Vision and Pattern RecognitionAdvancements in Visual Document Understanding with SynthDoc

SynthDoc creates synthetic documents for machine learning in document reading.

Chuanghao Ding, Xuejing Liu, Wei Tang

2025-06-22T09:13:06+00:00 ― 6 min read

MultimediaNew Method for Predicting Emotions in Videos

This study presents a model to analyze emotional reactions to video content.

Mingwei Sun, Kunpeng Zhang

2025-06-21T12:56:30+00:00 ― 7 min read

Audio and Speech ProcessingCombining Voice and Face for Better Identity Recognition

This article discusses the benefits of merging voice and facial recognition systems.

Aref Farhadipour, Masoumeh Chapariniya, Teodora Vukovic

2025-06-21T08:24:30+00:00 ― 5 min read

Computer Vision and Pattern RecognitionSimplifying RGBA Image Generation with Alfie

A new method for creating RGBA images easily and effectively.

Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli

2025-06-21T06:45:12+00:00 ― 7 min read

Computer Vision and Pattern RecognitionKangaroo: A New Approach to Video Understanding

Kangaroo improves video analysis by integrating visuals, sounds, and text effectively.

Jiajun Liu, Yibing Wang, Hanghang Ma

2025-06-20T14:33:30+00:00 ― 5 min read

Computer Vision and Pattern RecognitionA New Approach to Referring Image Segmentation

This paper presents a single-encoder model for improved image segmentation based on text descriptions.

Seonghoon Yu, Ilchae Jung, Byeongju Han

2025-06-20T14:09:48+00:00 ― 6 min read

SoundAdvancements in Target Speaker Extraction Technology

New methods improve voice separation in noisy environments.

Tathagata Bandyopadhyay

2025-06-20T13:47:05+00:00 ― 5 min read

Computer Vision and Pattern RecognitionImproving Image Captioning with Causal Inference

A new framework enhances image captioning accuracy and reduces errors.

Qian Cao, Xu Chen, Ruihua Song

2025-06-20T09:09:36+00:00 ― 5 min read

MultimediaAdvancing Multimodal Interaction Systems

Improving how machines assist users through better interaction and response measures.

Dan Bohus, Sean Andrist, Yuwei Bao

2025-06-19T23:48:42+00:00 ― 5 min read

Human-Computer InteractionMetaDigiHuman: A New Way to Connect in the Metaverse

Exploring digital humans and haptic interfaces for immersive interactions.

Senthil Kumar Jagatheesaperumal, Praveen Sathikumar, Harikrishnan Rajan

2025-06-18T20:09:42+00:00 ― 5 min read

Image and Video ProcessingImproving Video Data Transmission Through Smart Predictions

New methods enhance video transmission by predicting missing data effectively.

John Li, Shehab Sarar Ahmed, Deepak Nair

2025-06-18T18:03:35+00:00 ― 5 min read

SoundDynamic Background Music Generation for Interactive Media

A framework for real-time music adjustment in games and films.

Haoxuan Liu, Zihao Wang, Haorong Hong

2025-06-18T10:46:20+00:00 ― 5 min read

MultimediaAdvances in Generative Face Video Coding

MRDAC improves face video quality and compression using multiple reference frames.

Goluck Konuko, Giuseppe Valenzise

2025-06-18T07:23:24+00:00 ― 6 min read

SoundUsing Ultrasonic Sounds for Indoor Distance Measurement

Researchers explore ultrasonic echoes for accurate distance measurements in quiet indoor settings.

Junpei Honma, Akisato Kimura, Go Irie

2025-06-18T04:17:40+00:00 ― 6 min read

Computer Vision and Pattern RecognitionThe Role of Shadows in Image Processing

Exploring shadow detection, removal, and generation in computer vision.

Xiaowei Hu, Zhenghao Xing, Tianyu Wang

2025-06-17T23:21:30+00:00 ― 7 min read

Computer Vision and Pattern RecognitionImproving Image Clarity in Bad Weather

A new method enhances image quality during adverse weather using language and vision models.

Jiaqi Xu, Mengyang Wu, Xiaowei Hu

2025-06-17T23:05:42+00:00 ― 5 min read

MultimediaA New Framework for Privacy in Mobile Cloud Computing

This framework enhances multimedia app efficiency while protecting user privacy.

Zhongze Tang, Mengmei Ye, Yao Liu

2025-06-17T15:51:12+00:00 ― 7 min read

Computation and LanguageLongLLaVA: A New Era in Image Processing

LongLLaVA improves multi-image understanding for various applications.

Xidong Wang, Dingjie Song, Shunian Chen

2025-06-17T07:57:12+00:00 ― 5 min read

Computer Vision and Pattern RecognitionSegTalker: Advancing Talking Face Technology

SegTalker enhances talking face videos with realistic textures and easy editing.

Lingyu Xiong, Xize Cheng, Jintao Tan

2025-06-16T15:21:48+00:00 ― 5 min read

Computer Vision and Pattern RecognitionHiSC4D: A New Approach to Motion Capture

HiSC4D captures human movement using wearable sensors for better interaction analysis.

Yudi Dai, Zhiyong Wang, Xiping Lin

2025-06-16T02:27:36+00:00 ― 7 min read

Computer Vision and Pattern RecognitionAdvancing Question-Answering for Dense Video Events

Introducing a method to improve question-answering in videos with multiple events.

Hangyu Qin, Junbin Xiao, Angela Yao

2025-06-16T02:19:42+00:00 ― 6 min read

SoundAdvancements in Audio-Visual Speaker Diarization

An overview of audio-visual speaker diarization methods, challenges, and systems.

Victoria Mingote, Alfonso Ortega, Antonio Miguel

2025-06-15T21:14:00+00:00 ― 5 min read

Computer Vision and Pattern RecognitionAdvancements in Vision-Language Model Performance

This work enhances vision-language models through improved data strategies and innovative techniques.

Yuan Liu, Zhongyin Zhao, Ziyuan Zhuang

2025-06-15T18:02:00+00:00 ― 7 min read

Computer Vision and Pattern RecognitionAdvancing Visual Grounding with MMCA

A new method improves object identification in images through tailored visual and text integration.

Ruilin Yao, Shengwu Xiong, Yichen Zhao

2025-06-15T09:12:42+00:00 ― 5 min read

MultimediaImproving Meme Classification with SimCLIP

SimCLIP enhances meme analysis by effectively combining text and images.

Javier Huertas-Tato, Christos Koutlis, Symeon Papadopoulos

2025-06-15T01:42:24+00:00 ― 6 min read

Computer Vision and Pattern RecognitionIdentifying the Most Important Person in Social Images

MIP-GAF dataset helps analyze social dynamics in images.

Surbhi Madan, Shreya Ghosh, Lownish Rai Sookha

2025-06-14T02:24:06+00:00 ― 5 min read

Computer Vision and Pattern RecognitionImproving Vision-Language Models with Compositional Alignment

A new approach refines the connection between images and text in VLMs.

Ali Abdollah, Amirmohammad Izadi, Armin Saghafian

2025-06-13T05:12:12+00:00 ― 5 min read

SoundConnecting Art and Music Through Emotions

Research links paintings to music by interpreting emotions.

Tanisha Hisariya, Huan Zhang, Jinhua Liang

2025-06-12T23:35:50+00:00 ― 6 min read

MultimediaNew Method for Detecting Human Emotions

A study reveals a new way to identify emotions using video, sound, and text.

Jiehui Jia, Huan Zhang, Jinhua Liang

2025-06-12T23:24:36+00:00 ― 5 min read

Computer Vision and Pattern RecognitionEnhancing Speech Recognition with Multiple Input Types

This article explores how varied inputs can boost speech recognition accuracy.

Yiwen Guan, Viet Anh Trinh, Vivek Voleti

2025-06-12T15:30:00+00:00 ― 5 min read

Audio and Speech ProcessingTransforming Music Education with LLaQo

LLaQo offers detailed feedback for music performance assessment, enhancing student learning.

Huan Zhang, Vincent Cheung, Hayato Nishioka

2025-06-12T02:32:40+00:00 ― 5 min read

Networking and Internet ArchitectureStarlink and the Future of Video Streaming

Exploring how Starlink influences video streaming globally.

Liz Izhikevich, Reese Enghardt, Te-Yuan Huang

2025-06-11T20:33:00+00:00 ― 5 min read

SoundThe Growing Role of AI in Music Creation

Artificial intelligence is reshaping music with new tools and approaches.

Megan Wei, Mateusz Modrzejewski, Aswin Sivaraman

2025-06-11T07:55:15+00:00 ― 6 min read