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-articleJuly 2024
Short Video Ordering via Position Decoding and Successor Prediction
SIGIR '24: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information RetrievalJuly 2024, Pages 2167–2176https://doi.org/10.1145/3626772.3657795Short video collection is an easy way for users to consume coherent content on various online short video platforms, such as TikTok, YouTube, Douyin, and WeChat Channel. These collections cover a wide range of content, including online courses, TV series,...
- research-articleOctober 2023
Learning Event-Specific Localization Preferences for Audio-Visual Event Localization
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 3446–3454https://doi.org/10.1145/3581783.3612506Audio-Visual Event Localization (AVEL) aims to locate events that are both visible and audible in a video. Existing AVEL methods primarily focus on learning generic localization patterns that are applicable to all events. However, events often exhibit ...
- research-articleApril 2023
Learning Robust Multi-Modal Representation for Multi-Label Emotion Recognition via Adversarial Masking and Perturbation
WWW '23: Proceedings of the ACM Web Conference 2023April 2023, Pages 1510–1518https://doi.org/10.1145/3543507.3583258Recognizing emotions from multi-modal data is an emotion recognition task that requires strong multi-modal representation ability. The general approach to this task is to naturally train the representation model on training data without intervention. ...
- research-articleApril 2023
A Consistent Dual-MRC Framework for Emotion-cause Pair Extraction
ACM Transactions on Information Systems (TOIS), Volume 41, Issue 4Article No.: 105, Pages 1–27https://doi.org/10.1145/3558548Emotion-cause pair extraction (ECPE) is a recently proposed task that aims to extract the potential clause pairs of emotions and its corresponding causes in a document. In this article, we propose a new paradigm for the ECPE task. We cast the task as a ...
- research-articleFebruary 2023
Controlling class layout for deep ordinal classification via constrained proxies learning
AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial IntelligenceFebruary 2023, Article No.: 276, Pages 2483–2491https://doi.org/10.1609/aaai.v37i2.25345For deep ordinal classification, learning a well-structured feature space specific to ordinal classification is helpful to properly capture the ordinal nature among classes. Intuitively, when Euclidean distance metric is used, an ideal ordinal layout in ...
- research-articleFebruary 2022
Siamese Adversarial Network for image classification of heavy mineral grains
Computers & Geosciences (CGEO), Volume 159, Issue CFeb 2022https://doi.org/10.1016/j.cageo.2021.105016AbstractThe identification of heavy mineral grains based on microscopic images can significantly reduce the time and economic cost of the identification. There are several deep learning models to realize end-to-end identification of mineral ...
Highlights- A Siamese Adversarial Network model (SAN) is proposed for the image classification of heavy mineral grains.
- research-articleNovember 2021
SiamFuseNet: A pseudo-siamese network for detritus detection from polarized microscopic images of river sands
Computers & Geosciences (CGEO), Volume 156, Issue CNov 2021https://doi.org/10.1016/j.cageo.2021.104912AbstractDetecting detritus from the polarized microscopic images of river sands is the first step in the tasks of sediment source analysis, tectonic evolution, and lithofacies paleogeography. Traditional detritus detection mainly relies on ...
Highlights- A pesudo-siamese network named SiamFuseNet is proposed for the detritus detection.