Songlong Xing

发表

Constrained LSTM and Residual Attention for Image Captioning

Haifeng Hu, Liang Yang, Songlong Xing, 2020, ACM Trans. Multim. Comput. Commun. Appl..

Locally Confined Modality Fusion Network With a Global Perspective for Multimodal Human Affective Computing

Songlong Xing, Sijie Mai, Haifeng Hu, 2020, IEEE Transactions on Multimedia.

Divide, Conquer and Combine: Hierarchical Feature Fusion Network with Local and Global Perspectives for Multimodal Affective Computing

Songlong Xing, Sijie Mai, Haifeng Hu, 2019, ACL.

Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion

Songlong Xing, Haifeng Hu, Sijie Mai, 2020, AAAI.

Efficient and Fast Real-World Noisy Image Denoising by Combining Pyramid Neural Network and Two-Pathway Unscented Kalman Filter

Songlong Xing, Zhengming Li, Haifeng Hu, 2020, IEEE Transactions on Image Processing.

Adapted Dynamic Memory Network for Emotion Recognition in Conversation

Haifeng Hu, Songlong Xing, Sijie Mai, 2020, IEEE Transactions on Affective Computing.

Multi-Fusion Residual Memory Network for Multimodal Human Sentiment Comprehension

Haifeng Hu, Songlong Xing, Sijie Mai, 2022, IEEE Transactions on Affective Computing.

Analyzing Unaligned Multimodal Sequence via Graph Convolution and Graph Pooling Fusion pdf

Songlong Xing, Haifeng Hu, Ying Zeng, 2020, ArXiv.

Analyzing Multimodal Sentiment Via Acoustic- and Visual-LSTM With Channel-Aware Temporal Convolution Network

Haifeng Hu, Songlong Xing, Sijie Mai, 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

A Unimodal Representation Learning and Recurrent Decomposition Fusion Structure for Utterance-level Multimodal Embedding Learning

Songlong Xing, Sijie Mai, Haifeng Hu, 2021 .