Technical Program

*** Last Update : 1 February, 2018 *** 

PDF Version: Program Detail | Timetable

Monday, 5 February PROGRAM

 

 

8.30-10.00

Session 0: Opening Session

(Napalai Room)

Chair: Thanarat Chalidabhongse

 

Welcome Speech

Assoc. Prof. Dr. Supot Techavorasinskun

Dean, Faculty of Engineering Chulalongkorn University

 

 Conference Report

Assoc. Prof. Dr. Supavadee Aramvith

General Co-Chairs, MMM 2018

Faculty of Engineering Chulalongkorn University

 

Keynote (1) 

 

Multimedia and Art in the Age of Creative AI

Prof. Ahmed Elgammal

Department of Computer Science

Rutgers University, USA

10.00-10.30

Refreshment Break

(Foyer)

10.30-12.00

Session 1: Best Paper Session

(Napalai Room)

Chairs: Chong-wah Ngo and Thanarat Chalidabhongse

 

1 .  [18] LOCO: Local Context based Faster R-CNN for Small Traffic Sign Detection

2 .  [86] Crowd Distribution Estimation with Multi-scale Recursive Convolutional Neural Network

3 .  [110] A Markov Network Based Passage Retrieval Method for Multimodal Question Answering in the Cultural Heritage Domain

4 .  [170] Frame-Based Classification of Operation Phases in Cataract Surgery Videos

12.00-14.00

Lunch

(Vimarn Suriya Room)

VBS preparation

(Dusit Thani Hall)

14.00-15.30

Session 2: Demo/Poster Fast Forward Session

(Napalai Room)

Chairs: Wolgang Huerst and Suvit Nakpeerayuth

15.30-16.00

Refreshment Break

(Foyer)

16.00-19.00

Session 3: Video Browser Showdown (VBS) Competition

(Dusit Thani Hall)

Chairs: Cathal Gurrin, Werner Bailer, Klaus Schoeffmann, Jakub Lokoc, Kunwadee Sripanidkulchai

 

1 .     [195] Enhanced VIREO KIS at VBS 2018

2 .     [184] Competitive Video Retrieval with vitrivr

3 .     [202] The ITEC Collaborative Video Search System at the Video Browser Showdown 2018

4 .     [192] Sketch-based Similarity Search for Collaborative Feature Maps               

5 .     [200] Video Search Based on Semantic Extraction and Locally Regional Object Proposal         

6 .     [189] Revisiting SIRET Video Retrieval Tool 

7 .     [201] Sloth Search System 

8 .     [188] VERGE IN VBS 2018   

9 .     [196] Fusing keyword search and visual exploration for untagged videos     

17.00-20.00

Welcome reception [International Cocktails]

(Dusit Thani Hall)


Tuesday, 6 February PROGRAM

 

 

 

9.00-10.00

Session 4: Keynote (2) (Napalai Room)

Chair: Yo-Song Ho

Perception of Visual Sentiment: From Experimental Psychology to Computational Modeling

Prof. Mohan Kankanhalli

School of Computing,

National University of Singapore

Singapore

 

10.00-10.30

Refreshment Break

Foyer

 

10.30-12.00

Session 5A: Music, Audio, Art

(Napalai Room)

Chair: Nisachon Tangsangiumvisai

Session 5B: Multimedia Application

(Vimarn Suriya Room)

Chair: Cathal Gurrin

 

1 .  [21] Stitch-Based Image Stylization for Thread Art Using Sparse Modeling

2 .  [141] Towards Demographic-based Photographic Aesthetics Prediction for Portraitures

3 .  [48] An RNN-Based Speech-Music Discrimination Used for Hybrid Audio Coder

4 .  [5] Triplet Convolutional Network for Music Version Identification

1 .  [171] Multimodal Augmented Reality – Augmenting Auditory-Tactile Feedback to Change the Perception of Thickness

2 .  [173] Spatiotemporal 3D Models of Aging Fruit from Multi-View Time-Lapse Videos

3 .  [91] Two-level Segment-based Bitrate Control for Live ABR Streaming

4 .  [9] Multi-Hypothesis-based Error Concealment for Whole Frame Loss in HEVC 

12.00-13.30

Lunch

(The Cellar)

 

13.30-15.00 

Session 6A: Quality Enhancement

(Napalai Room)

Chair: Thanarat Chalidabhongse

Session 6B: SS – Multimedia Analytics: Perspectives, Techniques and Applications

(Vimarn Suriya Room)

Chair: Björn Þór Jónsson

 

1 .  [118] Parameter Selection for Denoising Algorithms Using NR-IQA with CNN

2 .  [100] Co-occurrent Structural Edge Detection for Color-Guided Depth Map Super-resolution

3 .  [19] Shallow-water Image Enhancement Using Relative Global Histogram Stretching Based on Adaptive Parameter Acquisition

4 .  [97] The CAMETRON lecture recording system: High quality video recording and editing with minimal human supervision 

1 .  [158] Rethinking Summarization and Storytelling for Modern Social Multimedia

2 .  [63] On the Traceability of Results from Deep Learning-based Cloud Services

3 .  [64] Category Specific Post Popularity Prediction

4 .  [167] Image Aesthetics and Content in Selecting Memorable Keyframes from Lifelogs

5 .  [46] Approaches for Event Segmentation of Visual Lifelog Data

15.00-16.30 

Session 7A: Face and Text Processing

(Napalai Room)

Chair: Takao Onoye

Session 7B: Indexing and Classification

(Vimarn Suriya Room)

Chair: Bernd Münzer

 

1 .  [150] Teacher and Student Joint Learning for Compact Facial Landmark Detection Network

2 .  [34] Font Recognition in Natural Images via Transfer Learning

3 .  [147] Uyghur Text Localization with Fast Component Detection

4 .  [94] Text Image Deblurring via Intensity Extremums Prior

1 .  [84] Learning to Index in Large-Scale Datasets

2 .  [10] Iterative Active Classification of Large Image Collection

3 .  [36] Cost-sensitive Deep Metric Learning for Fine-Grained Image Classification

16.30-17.00

Refreshment Break

(Foyer)

 

17.00-18.30

Session 8A: Video Search and Recognition

(Napalai Room)

Chair: Charnchai Pluempitiwiriyawej

Session 8B: Video and Image Processing

(Vimarn Suriya Room)

Chairs: Kanokphan Lertniphonphan and Manfred Jürgen Primus

 

1 .  [180] Evaluation of Visual Content Descriptors for Supporting Ad-Hoc Video Search Tasks at the Video Browser Showdown

2 .  [104] A Novel 3D Human Action Recognition Framework for Video Content Analysis

3 .  [102] Multi-Stream Fusion Model for Social Relation Recognition from Videos

1 .  [132] A motion-driven approach for fine-grained temporal segmentation of user-generated videos

2 .  [164] Real-Time Polyps Segmentation for Colonoscopy Video Frames Using Compressed Fully Convolutional Network

3 .  [124] Find me a sky: a data-driven method for color-consistent sky search & replacement

4 .  [39] Remote Sensing Image Fusion Based on Two-stream Fusion Network

19.00-21.00

 

MMM 2018 Banquet

(Dusit Thani Hall)

MC: Proadpran Punyabukkana

 

 

Wednesday, 7 February PROGRAM

 

 

 

9.00-10.00

Session 9: Keynote (3)  (Napalai Room)

Chair: Supavadee Aramvith

 

Multimodal Social Signals Analysis

Prof. Nicu Sebe

Department of Information Engineering and Computer Science

University of Trento

Italy

 

10.00-10.30

Refreshment Break

(Foyer)

 

10.30-12.00

Session 10A: Cross-modal Retrieval and Processing

(The Cellar)

Chair: Klaus Schoeffmann

Session 10B: Visual Parsing and Tracking

(Vimarn Suriya Room)

Chair: Kai Barthel

 

1 .  [159] Efficient and Interactive Spatial-Semantic Image Retrieval

2 .  [35] Recursive Pyramid Network with Joint Attention for Cross-media Retrieval

3 .  [172] Improving the quality of video-to-language models by optimizing annotation of the training material

4 .  [52] Deep Convolutional Neural Network for Correlating Images and Sentences

1 .  [82] Reinforcing Pedestrian Parsing on Small Scale Dataset

2 .  [69] Deep Pedestrian Detection using Contextual Information and Multi-level Features

3 .  [65] REVT: Robust and Efficient Visual Tracking by Region-Convolutional Regression Network

4 .  [25] Collision-Free LSTM for Human Trajectory Prediction

12.00-13.30

Lunch

(22 Kitchen & Bar)

 

13.30-15.00 

Session 11A: Vision & Graphics

(The Cellar)

Chair: Suree Pumrin

Session 11B: Deep Learning and Its Applications

(Vimarn Suriya Room)

Chair: Peerapon Vateekul

 

1 .  [50] Light Field Foreground Matting Based on Defocus and Correspondence

2 .  [3] Dual-way Guided Depth Image Inpainting With RGBD Image Pairs

3 .  [15] High-Precision 3D Coarse Registration Using RANSAC and Randomly-Picked Rejections

4 .  [22] AGO: Accelerating Global Optimization for Accurate Stereo Matching

1 .  [149] Convolution with Logarithmic Filter Groups for Efficient Shallow CNN

2 .  [14] Image Aesthetic Distribution Prediction with Fully Convolutional Network

3 .  [140] A Method of weather radar echo extrapolation based on convolutional neural networks

4 .  [162] Adaptive Image Representation using Information Gain and Saliency: Application to Cultural Heritage Datasets

15.00-17.00 

Refreshment Break

(Foyer)

 

Session 12A: Poster Session

(Vimarn Suriya Room)

Chairs: Chong-Wah Ngo, Thanarat Chalidabhongse, Klaus Schoeffmann

Session 12B: Demonstration Session

(Vimarn Suriya Room)

Chairs: Wolfgang Huerst, Suvit Nakpeerayuth

 

1 .    [2] Scalable Bag of Selected Deep Features for Visual Instance Retrieval

2 .    [27] Efficient Two-layer Model towards Cover Song Identification

3 .    [32] Source Distortion Estimation for Wyner-Ziv Distributed Video Coding                 

4 .    [37] A Novel Frontal Facial Synthesis Algorithm based on Individual Residual Faces

5 .    [43] A Text Recognition and Retrieval System for e-Business Image Management

6 .    [53] ShapeCreator: 3D Shape Generation from Isomorphic Datasets Based on Autoencoder   

7 .     [57] k-Labelsets for Multimedia Classification with Global and Local Label Correlation

8 .    [58] Domain Invariant Subspace Learning for Cross-modal Retrieval                 

9 .    [72] Coarse-to-Fine Image Super-Resolution Using Convolutional Neural Networks

10 . [76] CNN-Based DCT-Like Transform for Image Compression

11 . [83] Data Augmentation for EEG-Based Emotion Recognition with Deep Convolutional Neural Networks

12 . [88] A New Accurate Image Denoising Method Based on Sparse Coding Coefficients

13 . [90] Fusion Networks for Air-writing Recognition

14 . [96] Cloud of Line Distribution and Random Forest Text Detection from Natural/Video Scene Images         

15 .  [98] Room Floor Plan Generation on a Project Tango Device

16 . [101] Person Re-identification by Incorporating PCA Loss in CNN

17 . [105] Ensemble System for First Person Interactive Action Recognition

18 . [108] SRN: The Movie Character Relationship Analysis via Social Network

19 . [111] Effective Action Detection using Temporal Context and Posterior Probability of Length

20 . [115] Vehicle Semantics Extraction and Retrieval for Long-term Carpark Video Surveillance

21 . [117] Implicit Affective Video Tagging using Pupillary Response                

22 .  [122] Accurate Detection for Scene Texts with a Cascaded CNN Networks

23 . [127] Robust and Real-Time Visual Tracking based on Complementary Learners

24 . [135] The Long Tail of Web Video

25 . [151] Venue Prediction for Social Images by Exploiting Rich Temporal Patterns in LBSNs              

26 . [155] LVFS: a Lightweight Video Storage File System for IP Camera-based Surveillance Applications

27 . [160] Food Photo Recognition for Dietary Tracking: System and Experiment         

28 .  [169] SeqSense: video recommendation using topic sequence mining

 

1 .  [126] Lifelog Exploration Prototype in Virtual Reality              

2 .  [181] Auto accessory segmentation and interactive try-on system

3 .  [185] ActionVis: An Explorative Tool to Visualize Surgical Actions in Gynecologic Laparoscopy

4 .  [186] Automatic Smoke Classification in Endoscopic Video      

5 .  [187] Depth Representation of LiDAR Point Cloud with Adaptive Surface Patching for Object Classification

6 .  [190] Ontlus: 3D Content Collaborative Creation via Virtual Reality    

7 .  [191] Programmatic 3D Printing of a Revolving Camera Track to Automatically Capture Dense Images for 3D Scanning of Objects           

8 .  [193] Video Browsing on a Circular Timeline        

9 .  [194] Multi-Camera Microenvironment to Capture Multi-view Time-lapse Videos for 3D Analysis of Aging Objects 

10 .   [197] A Virtual Reality Interface for Interactions with Spatiotemporal 3D Data              

11 .   [198] AR DeepCalorieCam: An iOS App for Food Calorie Estimation with Augmented Reality         

12 .   [199] ImageX – Explore and search local/private images               

 

17.00-17.30

 

Closing Session

(Vimarn Suriya Room)

Chair: Supavadee Aramvith