Analyzing stress and depression can enhance our understanding of mental health.
― 6 min read
Computer Science - Multimedia
RSSA new model identifies funny moments in videos using visual, audio, and text data.
― 6 min read
AesopAgent enables users to create videos from stories using advanced AI tools.
― 5 min read
Examining how images impact learning in Wikipedia articles.
― 5 min read
A method to reduce redundancy in multi-view data representations.
― 6 min read
CoAVT integrates audio, visual, and text data for enhanced understanding.
― 7 min read
Create talking avatar videos easily with Virbo's innovative system.
― 6 min read
WiMANS dataset enables tracking of multiple users' activities using WiFi signals.
― 7 min read
A new framework simplifies video editing tasks using image editing tools.
― 8 min read
BDoG improves AI reasoning by integrating various data types effectively.
― 7 min read
Heracles combines transformers and state space models for improved data processing.
― 6 min read
A new method integrates acoustic information into language models for better speech recognition.
― 8 min read
Using music to explain cancer can enhance understanding and engagement.
― 6 min read
A new framework improves knowledge graph completion with diverse data types.
― 8 min read
A new way to animate portraits with changing expressions and angles.
― 7 min read
New method enhances 3D data compression while maintaining quality.
― 8 min read
CIRP enhances item representation for better online product bundling.
― 8 min read
Exploring how IoS could transform our digital experiences by engaging all senses.
― 10 min read
DIBS enhances video event captioning by refining boundaries using unlabeled data.
― 7 min read
Combining images and text improves accuracy in 3D depth estimation.
― 7 min read
WebXR transforms how we engage with immersive digital environments.
― 8 min read
New method enhances speech synthesis for individuals who cannot speak.
― 6 min read
AniFrame makes programming art accessible for newcomers with an easy-to-use approach.
― 6 min read
New dataset enhances image generation from complex news captions.
― 6 min read
A new method improves fact-checking of claims on social media.
― 6 min read
Shotit enables users to find videos quickly using images, streamlining the search process.
― 6 min read
A new framework for enhancing recommendations without prior data.
― 7 min read
Pegasus-1 allows users to interact with videos using natural language.
― 6 min read
GaussianTalker offers natural lip synchronization and high-quality visuals for talking head videos.
― 6 min read
A new approach allows machines to identify comic characters without prior training.
― 6 min read
Mimosa simplifies spatial audio creation for amateur video makers.
― 7 min read
The AIS 2024 Challenge seeks to improve video quality assessments using deep learning.
― 5 min read
GaussianTalker transforms digital interaction with lifelike talking heads.
― 6 min read
Subtitles are becoming essential for enhancing viewer experience in streaming services.
― 7 min read
Research introduces innovative techniques to improve detection of deepfake videos.
― 6 min read
A new dataset improves how robots interpret real-world environments.
― 6 min read
UniAV combines action localization, sound detection, and audio-visual event localization for better video understanding.
― 7 min read
A new method improves object detection performance using adaptive queries.
― 7 min read
Exploring human ability to identify deepfake videos compared to AI detection.
― 6 min read
Exploring how AI is transforming video production processes for filmmakers.
― 6 min read