Multimodal Visual Concept Learning with Weakly Supervised Techniques
This work addresses the challenge of leveraging natural language descriptions for video concept recognition, which is important for applications in multimedia analysis, but it is incremental as it builds upon existing Multiple Instance Learning frameworks.
The paper tackled the problem of automatically recognizing video concepts using textual cues as weak supervision, introducing two novel weakly supervised techniques (FSMIL and PLMIL) that extend Multiple Instance Learning, and showed that these methods considerably outperform state-of-the-art weakly supervised approaches on face and action recognition tasks using the COGNIMUSE database.
Despite the availability of a huge amount of video data accompanied by descriptive texts, it is not always easy to exploit the information contained in natural language in order to automatically recognize video concepts. Towards this goal, in this paper we use textual cues as means of supervision, introducing two weakly supervised techniques that extend the Multiple Instance Learning (MIL) framework: the Fuzzy Sets Multiple Instance Learning (FSMIL) and the Probabilistic Labels Multiple Instance Learning (PLMIL). The former encodes the spatio-temporal imprecision of the linguistic descriptions with Fuzzy Sets, while the latter models different interpretations of each description's semantics with Probabilistic Labels, both formulated through a convex optimization algorithm. In addition, we provide a novel technique to extract weak labels in the presence of complex semantics, that consists of semantic similarity computations. We evaluate our methods on two distinct problems, namely face and action recognition, in the challenging and realistic setting of movies accompanied by their screenplays, contained in the COGNIMUSE database. We show that, on both tasks, our method considerably outperforms a state-of-the-art weakly supervised approach, as well as other baselines.