The two-volume set LNCS 10735 and 10736 constitutes the thoroughly refereed proceedings of the 18th Pacific-Rim Conference on Multimedia, PCM 2017, held in Harbin, China, in September 2017.

The 184 full papers presented were carefully reviewed and selected from 264 submissions. The papers are organized in topical sections on: Best Paper Candidate; Video Coding; Image Super-resolution, Debluring, and Dehazing; Person Identity and Emotion; Tracking and Action Recognition; Detection and Classification; Multimedia Signal Reconstruction and Recovery; Text and Line Detection/Recognition; Social Media; 3D and Panoramic Vision; Deep Learning for Signal Processing and Understanding; Large-Scale Multimedia Affective Computing; Sensor-enhanced Multimedia Systems; Content Analysis; Coding, Compression, Transmission, and Processing.

The two-volume set LNCS 10735 and 10736 constitutes the thoroughly refereed proceedings of the 18th Pacific-Rim Conference on Multimedia, PCM 2017, held in Harbin, China, in September 2017.

The 184 full papers presented were carefully reviewed and selected from 264 submissions. The papers are organized in topical sections on: Best Paper Candidate; Video Coding; Image Super-resolution, Debluring, and Dehazing; Person Identity and Emotion; Tracking and Action Recognition; Detection and Classification; Multimedia Signal Reconstruction and Recovery; Text and Line Detection/Recognition; Social Media; 3D and Panoramic Vision; Deep Learning for Signal Processing and Understanding; Large-Scale Multimedia Affective Computing; Sensor-enhanced Multimedia Systems; Content Analysis; Coding, Compression, Transmission, and Processing.

The two-volume set LNCS 10735 and 10736 constitutes the thoroughly refereed proceedings of the 18th Pacific-Rim Conference on Multimedia, PCM 2017, held in Harbin, China, in September 2017.

The 184 full papers presented were carefully reviewed and selected from 264 submissions. The papers are organized in topical sections on: Best Paper Candidate; Video Coding; Image Super-resolution, Debluring, and Dehazing; Person Identity and Emotion; Tracking and Action Recognition; Detection and Classification; Multimedia Signal Reconstruction and Recovery; Text and Line Detection/Recognition; Social Media; 3D and Panoramic Vision; Deep Learning for Signal Processing and Understanding; Large-Scale Multimedia Affective Computing; Sensor-enhanced Multimedia Systems; Content Analysis; Coding, Compression, Transmission, and Processing.