Multimodal Technologies for Perception of Humans: International Evaluation Workshops CLEAR 2007 and RT 2007, Baltimore, MD, USA, May 8-11, 2007, Revis [Paperback]

This book constitutes the thoroughly refereed joint post-workshop proceedings of two co-located events: the Second International Workshop on Classification of Events, Activities and Relationships, CLEAR 2007, and the 5th Rich Transcription 2007 Meeting Recognition evaluation, RT 2007, held in succession in Baltimore, MD, USA, in May 2007. The workshops had complementary evaluation efforts; CLEAR for the evaluation of human activities, events, and relationships in multiple multimodal data domains; and RT for the evaluation of speech transcription-related technologies from meeting room audio collections. The 35 revised full papers presented from CLEAR 2007 cover 3D person tracking, 2D face detection and tracking, person and vehicle tracking on surveillance data, vehicle and person tracking aerial videos, person identification, head pose estimation, and acoustic event detection. The 15 revised full papers presented from RT 2007 are organized in topical sections on speech-to-text, and speaker diarization.CLEAR 2007.- The CLEAR 2007 Evaluation.- The AIT 3D Audio / Visual Person Tracker for CLEAR 2007.- A Person Tracking System for CHIL Meetings.- An Appearance-Based Particle Filter for Visual Tracking in Smart Rooms.- Multi-level Particle Filter Fusion of Features and Cues for Audio-Visual Person Tracking.- Multispeaker Localization and Tracking in Intelligent Environments.- Multi-person Tracking Strategies Based on Voxel Analysis.- TUT Acoustic Source Tracking System 2007.- The AIT 2D Face Detection and Tracking System for CLEAR 2007.- PittPatt Face Detection and Tracking for the CLEAR 2007 Evaluation.- Tsinghua Face Detection and Tracking for CLEAR 2007 Evaluation.- The AIT Outdoor Tracker for Vehicles and Pedestrians in CLEAR2007.- Objective Evaluation of Pedestrian and Vehicle Tracking on the CLEAR Surveillance Dataset.- Person and Vehicle Tracking in Surveillance Video.- UMD_VDT, an Integration of Detection and Tracking Methods for Multiple Human Tracking.- CLEAR07lã,