Personal profile
Fingerprint
- 1 Similar Profiles
Collaborations and top research areas from the last five years
-
A Comparative Study of Emotion Recognition Systems: From Classical Approaches to Multimodal Large Language Models
Grosu, M. M., Datcu, O., Tapu, R. & Mocanu, B., 1 Feb 2026, In: Applied Sciences (Switzerland). 16, 3, 1289.Research output: Contribution to journal › Review article › peer-review
Open Access -
Automatic Audio Description: A Training-Free Approach Using Foundation Models
Tapu, R. & Mocanu, B., 1 Jan 2026, Computer Analysis of Images and Patterns - 21st International Conference, CAIP 2025, Proceedings. Castrillón-Santana, M., Travieso-González, C. M., Freire-Obregón, D., Hernández-Sosa, D., Lorenzo-Navarro, J., Santana, O. J. & Deniz Suarez, O. (eds.). Springer Science and Business Media Deutschland GmbH, p. 173-183 11 p. (Lecture Notes in Computer Science; vol. 15622 LNCS).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
-
Seeing Through Words: A Zero-Shot Multimodal Audio Description System with Foundation Models
Mocanu, B. & Tapu, R., 1 Jan 2026, Advances in Visual Computing - 20th International Symposium, ISVC 2025, Proceedings. Bebis, G., Ye, J., Wang, Y., Konakovic Lukovic, M., Kalantari, N. K., Cho, I., Yang, Y., Dimara, E. & Brehmer, M. (eds.). Springer Science and Business Media Deutschland GmbH, p. 85-97 13 p. (Lecture Notes in Computer Science; vol. 16397 LNCS).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
-
A Lightweight Audio-Visual Speaker Detection System for Assistive Video Captioning
Mocanu, B. & Tapu, R., 1 Jan 2025, 2025 13th European Workshop on Visual Information Processing, EUVIP 2025. Institute of Electrical and Electronics Engineers Inc., (Proceedings - European Workshop on Visual Information Processing, EUVIP).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
-
Multimodal active speaker detection using cross-Attention and contextual information
Mocanu, B. & Tapu, R., 1 Jan 2024, 2024 IEEE International Conference on Consumer Electronics, ICCE 2024. Institute of Electrical and Electronics Engineers Inc., (Digest of Technical Papers - IEEE International Conference on Consumer Electronics).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
-
SemanticAd: A Multimodal Contextual Advertisement Framework for Online Video Streaming Platforms
Mocanu, B. & Tapu, R., 1 Jan 2024, In: IEEE Access. 12, p. 63142-63155 14 p.Research output: Contribution to journal › Article › peer-review
Open Access -
Vessel-based lung lobe partitioning in ultra-short time echo proton MRI for regional ventilation assessment
Khiati, R. N., Didier, A., Barrau, N., Justet, A., Maître, X., Bernaudin, J. F., Brillet, P. Y., Tapu, R., Ispas, R. & Fetita, C., 1 Jan 2024, Medical Imaging 2024: Computer-Aided Diagnosis. Chen, W. & Astley, S. M. (eds.). SPIE, 1292708. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; vol. 12927).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
Open Access -
Conditional Cross Correlation Network for Video Question Answering
Ouenniche, K., Tapu, R. & Zaharia, T., 1 Jan 2023, Proceedings - 17th IEEE International Conference on Semantic Computing, ICSC 2023. Institute of Electrical and Electronics Engineers Inc., p. 25-32 8 p. (Proceedings - 17th IEEE International Conference on Semantic Computing, ICSC 2023).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
Open Access -
Facial Emotion Recognition using Video Visual Transformer and Attention Dropping
Mocanu, B. & Tapu, R., 1 Jan 2023, 2023 International Symposium on Signals, Circuits and Systems, ISSCS 2023. Institute of Electrical and Electronics Engineers Inc., (2023 International Symposium on Signals, Circuits and Systems, ISSCS 2023).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
-
Multimodal emotion recognition using cross modal audio-video fusion with attention and deep metric learning
Mocanu, B., Tapu, R. & Zaharia, T., 1 May 2023, In: Image and Vision Computing. 133, 104676.Research output: Contribution to journal › Article › peer-review
Open Access