Tampere University of Technology

TUTCRIS Research Portal

Cross-granularity graph inference for semantic video object segmentation

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Cross-granularity graph inference for semantic video object segmentation. / Wang, Huiling; Wang, Tinghuai; Chen, Ke; Kämäräinen, Joni-Kristian.

26th International Joint Conference on Artificial Intelligence, IJCAI 2017. 2017. p. 4544-4550.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Wang, H, Wang, T, Chen, K & Kämäräinen, J-K 2017, Cross-granularity graph inference for semantic video object segmentation. in 26th International Joint Conference on Artificial Intelligence, IJCAI 2017. pp. 4544-4550, INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 1/01/00.

APA

Wang, H., Wang, T., Chen, K., & Kämäräinen, J-K. (2017). Cross-granularity graph inference for semantic video object segmentation. In 26th International Joint Conference on Artificial Intelligence, IJCAI 2017 (pp. 4544-4550)

Vancouver

Wang H, Wang T, Chen K, Kämäräinen J-K. Cross-granularity graph inference for semantic video object segmentation. In 26th International Joint Conference on Artificial Intelligence, IJCAI 2017. 2017. p. 4544-4550

Author

Wang, Huiling ; Wang, Tinghuai ; Chen, Ke ; Kämäräinen, Joni-Kristian. / Cross-granularity graph inference for semantic video object segmentation. 26th International Joint Conference on Artificial Intelligence, IJCAI 2017. 2017. pp. 4544-4550

Bibtex - Download

@inproceedings{497c00bb0c4b4f6cb589ec6c07faf2a0,
title = "Cross-granularity graph inference for semantic video object segmentation",
abstract = "We address semantic video object segmentation via a novel cross-granularity hierarchical graphical model to integrate tracklet and object proposal reasoning with superpixel labeling. Tracklet characterizes varying spatial-temporal relations of video object which, however, quite often suffers from sporadic local outliers. In order to acquire highquality tracklets, we propose a transductive inference model which is capable of calibrating shortrange noisy object tracklets with respect to longrange dependencies and high-level context cues. In the center of this work lies a new paradigm of semantic video object segmentation beyond modeling appearance and motion of objects locally, where the semantic label is inferred by jointly exploiting multi-scale contextual information and spatialtemporal relations of video object. We evaluate our method on two popular semantic video object segmentation benchmarks and demonstrate that it advances the state-of-the-art by achieving superior accuracy performance than other leading methods.",
author = "Huiling Wang and Tinghuai Wang and Ke Chen and Joni-Kristian K{\"a}m{\"a}r{\"a}inen",
year = "2017",
language = "English",
pages = "4544--4550",
booktitle = "26th International Joint Conference on Artificial Intelligence, IJCAI 2017",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Cross-granularity graph inference for semantic video object segmentation

AU - Wang, Huiling

AU - Wang, Tinghuai

AU - Chen, Ke

AU - Kämäräinen, Joni-Kristian

PY - 2017

Y1 - 2017

N2 - We address semantic video object segmentation via a novel cross-granularity hierarchical graphical model to integrate tracklet and object proposal reasoning with superpixel labeling. Tracklet characterizes varying spatial-temporal relations of video object which, however, quite often suffers from sporadic local outliers. In order to acquire highquality tracklets, we propose a transductive inference model which is capable of calibrating shortrange noisy object tracklets with respect to longrange dependencies and high-level context cues. In the center of this work lies a new paradigm of semantic video object segmentation beyond modeling appearance and motion of objects locally, where the semantic label is inferred by jointly exploiting multi-scale contextual information and spatialtemporal relations of video object. We evaluate our method on two popular semantic video object segmentation benchmarks and demonstrate that it advances the state-of-the-art by achieving superior accuracy performance than other leading methods.

AB - We address semantic video object segmentation via a novel cross-granularity hierarchical graphical model to integrate tracklet and object proposal reasoning with superpixel labeling. Tracklet characterizes varying spatial-temporal relations of video object which, however, quite often suffers from sporadic local outliers. In order to acquire highquality tracklets, we propose a transductive inference model which is capable of calibrating shortrange noisy object tracklets with respect to longrange dependencies and high-level context cues. In the center of this work lies a new paradigm of semantic video object segmentation beyond modeling appearance and motion of objects locally, where the semantic label is inferred by jointly exploiting multi-scale contextual information and spatialtemporal relations of video object. We evaluate our method on two popular semantic video object segmentation benchmarks and demonstrate that it advances the state-of-the-art by achieving superior accuracy performance than other leading methods.

M3 - Conference contribution

SP - 4544

EP - 4550

BT - 26th International Joint Conference on Artificial Intelligence, IJCAI 2017

ER -