Multimodal learning falls into the trap of the optimization dilemma due to the modality imbalance phenomenon, leading to unsatisfactory performance in real applications. A core reason for modality imbalance is that the models of each modality converge at different rates. Many attempts naturally focus on adjusting learning procedures adaptively. Essentially, the reason why models converge at different rates is because the difficulty of fitting category labels is inconsistent for each modality during learning. From the perspective of fitting labels, we find that appropriate positive intervention label fitting can correct this difference in learning ability. By exploiting the ability of contrastive learning to intervene in the learning of category label fitting, we propose a novel multimodal learning approach that dynamically integrates unsupervised contrastive learning and supervised multimodal learning to address the modality imbalance problem. We find that a simple yet heuristic integration strategy can significantly alleviate the modality imbalance phenomenon. Moreover, we design a learning-based integration strategy to integrate two losses dynamically, further improving the performance. Experiments on widely used datasets demonstrate the superiority of our method compared with state-of-the-art (SOTA) multimodal learning approaches.

In this paper, we focus on training and evaluating effective word embeddings with both text and visual information. More specifically, we introduce a large-scale dataset with 300 million sentences describing over 40 million images crawled and downloaded from publicly available Pins (i.e. an image with sentence descriptions uploaded by users) on Pinterest. This dataset is more than 200 times larger than MS COCO, the standard large-scale image dataset with sentence descriptions. In addition, we construct an evaluation dataset to directly assess the effectiveness of word embeddings in terms of finding semantically similar or related words and phrases. The word/phrase pairs in this evaluation dataset are collected from the click data with millions of users in an image search system, thus contain rich semantic relationships. Based on these datasets, we propose and compare several Recurrent Neural Networks (RNNs) based multimodal (text and image) models. Experiments show that our model benefits from incorporating the visual information into the word embeddings, and a weight sharing strategy is crucial for learning such multimodal embeddings.

Human perception of the empirical world involves recognizing the diverse appearances, or'modalities', of underlying objects.

Human perception of the empirical world involves recognizing the diverse appearances, or'modalities', of underlying objects.

You were awarded an Honourable Mention for the 2019 AAAI / ACM SIGAI Doctoral Dissertation Award. What was the topic of your dissertation research, and what were the main contributions or findings? My PhD dissertation was on the topic of Visual Question Answering, called VQA. We proposed the task of open-ended and free-form VQA - a new way to benchmark computer vision models by asking them questions about images. We curated a large-scale dataset for researchers to train and test their models on this task.

By inferring the correct answers for video-based questions, video question answering (VideoQA) has attracted increasing research attention due to its huge application potential, as a fundamental technique for vision-to-language reasoning. The task involves acquisition and manipulation of spatio-temporal visual representations guided by the compositional semantics of the linguistic clues[32,15,21,34]. Existingworkscanroughly be divided into two aspects.

However, considering the ever-evolving paradigms in deep learning, employees with ulterior motivesmay fabricate reasons such asthe requirements ofdata augmentation [6]orthe purpose of multimodal learning [3] to apply for relevant and irrelevant private datasets, which is common in social engineering [4].