Related papers: MDMMT: Multidomain Multimodal Transformer for Vide…
Building a general model capable of analyzing human trajectories across different geographic regions and different tasks becomes an emergent yet important problem for various applications. However, existing works suffer from the…
Partially relevant video retrieval (PRVR) is a practical yet challenging task in text-to-video retrieval, where videos are untrimmed and contain much background content. The pursuit here is of both effective and efficient solutions to…
Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps between common and rare concepts. To…
Long-tailed multi-label visual recognition (LTML) task is a highly challenging task due to the label co-occurrence and imbalanced data distribution. In this work, we propose a unified framework for LTML, namely prompt tuning with…
Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data. The most prominent tasks in this area…
While most current work in multimodal machine translation (MMT) uses the Multi30k dataset for training and evaluation, we find that the resulting models overfit to the Multi30k dataset to an extreme degree. Consequently, these models…
Prevailing joint prediction transformers for Video Highlight Detection and Moment Retrieval (HD/MR) exhibit deficiencies in handling cross-task dynamics, achieving robust video-text alignment, and utilizing effective attention mechanisms,…
Document translation poses a challenge for Neural Machine Translation (NMT) systems. Most document-level NMT systems rely on meticulously curated sentence-level parallel data, assuming flawless extraction of text from documents along with…
Audio and video are two most common modalities in the mainstream media platforms, e.g., YouTube. To learn from multimodal videos effectively, in this work, we propose a novel audio-video recognition approach termed audio video Transformer,…
Retrieving visual and textual information from medical literature and hospital records can enhance diagnostic accuracy for clinical image interpretation. However, multimodal retrieval-augmented diagnosis is highly challenging. We explore a…
Multitask learning has shown promising performance in many applications and many multitask models have been proposed. In order to identify an effective multitask model for a given multitask problem, we propose a learning framework called…
Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increasingly operate on paired vision-language inputs, multimodal distillation must preserve…
Building on the advances of language models, Large Multimodal Models (LMMs) have contributed significant improvements in video understanding. While the current video LMMs utilize advanced Large Language Models (LLMs), they rely on either…
The increasing amount of online videos brings several opportunities for training self-supervised neural networks. The creation of large scale datasets of videos such as the YouTube-8M allows us to deal with this large amount of data in…
Conventionally, spatiotemporal modeling network and its complexity are the two most concentrated research topics in video action recognition. Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity…
Given an untrimmed video and natural language query, video sentence grounding aims to localize the target temporal moment in the video. Existing methods mainly tackle this task by matching and aligning semantics of the descriptive sentence…
Until recently, the number of public real-world text images was insufficient for training scene text recognizers. Therefore, most modern training methods rely on synthetic data and operate in a fully supervised manner. Nevertheless, the…
In recent years, considerable progress on the task of text-video retrieval has been achieved by leveraging large-scale pretraining on visual and audio datasets to construct powerful video encoders. By contrast, despite the natural symmetry,…
Recently, Transformer-based methods have been utilized to improve the performance of human action recognition. However, most of these studies assume that multi-view data is complete, which may not always be the case in real-world scenarios.…
A neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information. Many recent studies report improvements when equipping…