Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleOctober 2019
Adaptive Ensemble: Solution to the Biomedia ACM MM GrandChallenge 2019
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 2583–2587https://doi.org/10.1145/3343031.3356078In this paper we share our solution to the Biomedia ACM MM Grand Challenge 2019, which focuses on the gastrointestinal tract with an aim to detect and classify abnormalities. We firstly identify the challenges in this task, including the scarce and ...
- research-articleOctober 2019
Enhancing Endoscopic Image Classification with Symptom Localization and Data Augmentation
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 2578–2582https://doi.org/10.1145/3343031.3356073Inspired by recent advances in computer vision and deep learning, we propose new enhancements to tackle problems appearing in endoscopic image analysis, especially abnormality finding and anatomical landmark detection. In details, a combination of ...
- research-articleOctober 2019
Latency Aware Adaptive Video Streaming using Ensemble Deep Reinforcement Learning
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 2647–2651https://doi.org/10.1145/3343031.3356071The development of live broadcasting represents many new technical challenges on adaptive bitrate(ABR) algorithms, which not only requires stable and high-quality transmission but also low end-to-end latency. Reinforcement learning(RL) achieves ...
- research-articleOctober 2019
Automatic Disease Detection and Report Generation for Gastrointestinal Tract Examination
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 2573–2577https://doi.org/10.1145/3343031.3356066In this paper, we present a method to automatically identify diseases from videos of gastrointestinal (GI) tract examinations using a Deep Convolutional Neural Network (DCNN) that processes images from digital endoscopes. Our goal is to aid domain ...
- research-articleOctober 2019
Continuous Bitrate & Latency Control with Deep Reinforcement Learning for Live Video Streaming
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 2637–2641https://doi.org/10.1145/3343031.3356063In this paper, we introduce a continuous bitrate control and latency control model for the Live Video Streaming Challenge. Our model is based on Deep Deterministic Policy Gradient, popular on continuous control tasks. Simultaneously, it can take a fine-...
-
- research-articleOctober 2019
ACM Multimedia BioMedia 2019 Grand Challenge Overview
- Steven Hicks,
- Michael Riegler,
- Pia Smedsrud,
- Trine B. Haugen,
- Kristin Ranheim Randel,
- Konstantin Pogorelov,
- Håkon Kvale Stensland,
- Duc-Tien Dang-Nguyen,
- Mathias Lux,
- Andreas Petlund,
- Thomas de Lange,
- Peter Thelin Schmidt,
- Pål Halvorsen
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 2563–2567https://doi.org/10.1145/3343031.3356058The BioMedia 2019 ACM Multimedia Grand Challenge is the first in a series of competitions focusing on the use of multimedia for different medical use-cases. In this year's challenge, the participants are asked to develop efficient algorithms which ...
- research-articleOctober 2019
Cross-modal Neural Sign Language Translation
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 1650–1654https://doi.org/10.1145/3343031.3352587Sign Language is the primary means of communication for the majority of the Deaf and hard-of-hearing communities. Current computational approaches in this general research area have focused specifically on sign language recognition and the translation ...
- tutorialOctober 2019
Medical Multimedia Systems and Applications
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 2711–2713https://doi.org/10.1145/3343031.3351319In recent years, we have observed a rise of interest in the multimedia community towards research topics related to health. It can be observed that this goes into two interesting directions. One is personal health with a larger focus on well-being and ...
- research-articleOctober 2019
Optimized Skeleton-based Action Recognition via Sparsified Graph Regression
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 601–610https://doi.org/10.1145/3343031.3351170With the prevalence of accessible depth sensors, dynamic human body skeletons have attracted much attention as a robust modality for action recognition. Previous methods model skeletons based on RNN or CNN, which has limited expressive power for ...
Reproducible Experiments on Adaptive Discriminative Region Discovery for Scene Recognition
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 1076–1079https://doi.org/10.1145/3343031.3351169This companion paper supports the replication of scene image recognition experiments using Adaptive Discriminative Region Discovery (Adi-Red), an approach presented at ACM Multimedia 2018. We provide a set of artifacts that allow the replication of the ...
On Reproducing Semi-dense Depth Map Reconstruction using Deep Convolutional Neural Networks with Perceptual Loss
- Ilya Makarov,
- Dmitrii Maslov,
- Olga Gerasimova,
- Vladimir Aliev,
- Alisa Korinevskaya,
- Ujjwal Sharma,
- Haoliang Wang
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 1080–1084https://doi.org/10.1145/3343031.3351167In our recent papers, we proposed a new family of residual convolutional neural networks trained for semi-dense and sparse depth reconstruction without use of RGB channel. The proposed models can be used in low-resolution depth sensors or SLAM methods ...
- research-articleOctober 2019
Domain-Specific Embedding Network for Zero-Shot Recognition
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 2070–2078https://doi.org/10.1145/3343031.3351092Zero-Shot Learning (ZSL) seeks to recognize a sample from either seen or unseen domain by projecting the image data and semantic labels into a joint embedding space. However, most existing methods directly adapt a well-trained projection from one domain ...
- research-articleOctober 2019
Multi-Level Fusion based Class-aware Attention Model for Weakly Labeled Audio Tagging
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 1304–1312https://doi.org/10.1145/3343031.3351090Recognizing ongoing events based on acoustic clues has been a critical research problem for a variety of AI applications. Compared to visual inputs, acoustic cues tend to be less descriptive and less consistent in time domain. The duration of a sound ...
- research-articleOctober 2019
On Learning Disentangled Representation for Acoustic Event Detection
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 2006–2014https://doi.org/10.1145/3343031.3351086Polyphonic Acoustic Event Detection (AED) is a challenging task as the sounds are mixed with the signals from different events, and the features extracted from the mixture do not match well with features calculated from sounds in isolation, leading to ...
- research-articleOctober 2019
Towards Optimal CNN Descriptors for Large-Scale Image Retrieval
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 1768–1776https://doi.org/10.1145/3343031.3351081Instance-level image retrieval is a long-standing and challenging problem in multimedia. Recently, fine-tuning Convolutional Neural Networks (CNNs) has become a promising direction, and a number of successful strategies based on global CNN descriptors ...
- research-articleOctober 2019
Ground-Aware Point Cloud Semantic Segmentation for Autonomous Driving
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 971–979https://doi.org/10.1145/3343031.3351076Semantic understanding of 3D scenes is essential for autonomous driving. Although a number of efforts have been devoted to semantic segmentation of dense point clouds, the great sparsity of 3D LiDAR data poses significant challenges in autonomous ...
- research-articleOctober 2019
FashionOn: Semantic-guided Image-based Virtual Try-on with Detailed Human and Clothing Information
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 275–283https://doi.org/10.1145/3343031.3351075The image-based virtual try-on system has attracted a lot of research attention. The virtual try-on task is challenging since synthesizing try-on images involves the estimation of 3D transformation from 2D images, which is an ill-posed problem. ...
- research-articleOctober 2019
Knowledge-guided Pairwise Reconstruction Network for Weakly Supervised Referring Expression Grounding
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 539–547https://doi.org/10.1145/3343031.3351074Weakly supervised referring expression grounding (REG) aims at localizing the referential entity in an image according to linguistic query, where the mapping between the image region (proposal) and the query is unknown in the training stage. In ...
- research-articleOctober 2019
Self-supervised Face-Grouping on Graphs
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 247–256https://doi.org/10.1145/3343031.3351071We propose a novel self-supervised method for fine-tuning deep face representations called Face-Grouping on Graphs. We apply our method to automatic face grouping, where characters are to be separated based on their identity. To solve this problem, a ...
- research-articleOctober 2019
GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOctober 2019, Pages 2170–2178https://doi.org/10.1145/3343031.3351068We focus on estimating the 3D orientation of the ground plane from a single image. We formulate the problem as an inter-mingled multi-task prediction problem by jointly optimizing for pixel-wise surface normal direction, ground plane segmentation, and ...