archive
Every paper Pith has read. Search by title, abstract, or pith.
378 papers in cs.MM · page 8
-
Models link face recognition accuracy to resolution
QRMODA and BRMODA: Novel Models for Face Recognition Accuracy in Computer Vision Systems with Adapted Video Streams
-
Deep learning predicts legislator ideology from Facebook photos
Understanding the Political Ideology of Legislators from Social Media Images
-
Fine-tuned CNNs match prior methods on ancient document retrieval
Deep Learning Approaches for Image Retrieval and Pattern Spotting in Ancient Documents
-
Model fuses X-ray views and medical concepts to generate reports
Automatic Radiology Report Generation based on Multi-view Image Fusion and Medical Concept Enrichment
-
Spike timing alone restores scene luminance for texture images
A Retina-inspired Sampling Method for Visual Texture Reconstruction
-
DREAMT model specifies six layers for AI storytelling
DREAMT -- Embodied Motivational Conversational Storytelling
-
Generalized extreme value distribution fits live TV bit rates best
The Statistical Analysis of the Live TV Bit Rate
-
Imitation learning teaches AI basic film editing rules
Towards Data-Driven Automatic Video Editing
-
Neural networks generate new dance sequences from 3D motion points
Beyond Imitation: Generative and Variational Choreography via Machine Learning
-
GAN embeds secret audio inside carrier audio at high fidelity
Heard More Than Heard: An Audio Steganography Method Based on GAN
-
Pre-training on MIDI improves NES music generation
LakhNES: Improving multi-instrumental music generation with cross-domain pre-training
-
1964 algorithmic program recreated for three new pieces
Learning from History: Recreating and Repurposing Sister Harriet Padberg's Computer Composed Canon and Free Fugue
-
Binary attention embeds more secret data while preserving task features
BASN -- Learning Steganography with Binary Attention Mechanism
-
Fragile fingerprints resist planting attacks at typical compression
On the Security and Applicability of Fragile Camera Fingerprints
-
TrackNet tracks tennis ball at 99.7% precision on broadcast video
TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications
-
Review finds underwater image methods have persistent shortcomings
An Experimental-based Review of Image Enhancement and Image Restoration Methods for Underwater Imaging
-
Compensation protocol fixes Unity timing issues for AV research
Synchronizing Audio-Visual Film Stimuli in Unity (version 5.5.1f1): Game Engines as a Tool for Research
-
Bilinear CNN fuses two networks for blind quality scoring
Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
-
ResNet detects replays at 1.08% EER using perturbed group delay grams
The DKU Replay Detection System for the ASVspoof 2019 Challenge: On Data Augmentation, Feature Representation, Classification, and Fusion
-
Hierarchical VAE-GAN generates 136-beat melodies with form
MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
-
Cognitive models plus multi-agent rules raise game music immersion
Adaptive Music Composition for Games
-
Disentangling flows organize synthesizer latent space
Universal audio synthesizer control with normalizing flows
-
Visual bookmarks strengthen scent in image recommendations
Effects of Foraging in Personalized Content-based Image Recommendation
-
Performance traits shape music perception more than the score
Music Performance Analysis: A Survey
-
Blockchain lets one rhythm game pull enemies from others
Rhythm Dungeon: A Blockchain-based Music Roguelike Game
-
AR virtual humans dodge real non-users with natural shifts
Non-user Inclusive Design for Maintaining Harmony of Real-Virtual Human Interaction in Augmented Reality
-
Randomized subsets recover camera from Patch-Match images
PRNU Based Source Camera Attribution for Image Sets Anonymized with Patch-Match Algorithm
-
Artist album track metadata trains music representations
Representation Learning of Music Using Artist, Album, and Track Information
-
Music motion game supports elderly cognitive and motor function
A novel music-based game with motion capture to support cognitive and motor function in the elderly
-
Music listening on one app predicts location and pet choices on another
Cross-Platform Modeling of Users' Behavior on Social Media
-
Scattering coefficients re-synthesize audio textures and enable new effects
The Shape of RemiXXXes to Come: Audio Texture Synthesis with Time-frequency Scattering
-
Zero-shot learning transfers across music corpora
Zero-shot Learning and Knowledge Transfer in Music Classification and Tagging
-
Eight classes organize semantic image-text relations
Understanding, Categorizing and Predicting Semantic Image-Text Relations
-
Tile visibility probabilities near-optimize 360-video rates
Probabilistic Tile Visibility-Based Server-Side Rate Adaptation for Adaptive 360-Degree Video Streaming
-
ML viewer forecasts guide proactive cloud allocation for live streams
QoE-Aware Resource Allocation for Crowdsourced Live Streaming: A Machine Learning Approach
-
Joint training boosts keyword spotting in noise
A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting
-
Statistical models from annotated lights restore underwater images faster
Enhancement of Underwater Images with Statistical Model of Background Light and Optimization of Transmission Map