Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval

• URL: http://arxiv.org/abs/2112.04446v1
• Date: Wed, 8 Dec 2021 18:14:57 GMT
• Title: Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval
• Authors: Nina Shvetsova, Brian Chen, Andrew Rouditchenko, Samuel Thomas, Brian Kingsbury, Rogerio Feris, David Harwath, James Glass, Hilde Kuehne
• Abstract summary: Multi-modal learning from video data has seen increased attention recently as it allows to train semantically meaningful embeddings without human annotation. We present a multi-modal, modality fusion transformer approach that learns to exchange information between multiple modalities, such as video, audio, and text, and integrate them into a joined multi-modal representation.
• Score: 36.50847375135979
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-modal learning from video data has seen increased attention recently as it allows to train semantically meaningful embeddings without human annotation enabling tasks like zero-shot retrieval and classification. In this work, we present a multi-modal, modality agnostic fusion transformer approach that learns to exchange information between multiple modalities, such as video, audio, and text, and integrate them into a joined multi-modal representation to obtain an embedding that aggregates multi-modal temporal information. We propose to train the system with a combinatorial loss on everything at once, single modalities as well as pairs of modalities, explicitly leaving out any add-ons such as position or modality encoding. At test time, the resulting model can process and fuse any number of input modalities. Moreover, the implicit properties of the transformer allow to process inputs of different lengths. To evaluate the proposed approach, we train the model on the large scale HowTo100M dataset and evaluate the resulting embedding space on four challenging benchmark datasets obtaining state-of-the-art results in zero-shot video retrieval and zero-shot video action localization.

Related papers

• StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation [63.31007867379312]
  We propose StitchFusion, a framework that integrates large-scale pre-trained models directly as encoders and feature fusers. We introduce a multi-directional adapter module (MultiAdapter) to enable cross-modal information transfer during encoding. Our model achieves state-of-the-art performance on four multi-modal segmentation datasets with minimal additional parameters.
  arXiv  Detail & Related papers  (2024-08-02T15:41:16Z)
• VIMI: Grounding Video Generation through Multi-modal Instruction [89.90065445082442]
  Existing text-to-video diffusion models rely solely on text-only encoders for their pretraining. We construct a large-scale multimodal prompt dataset by employing retrieval methods to pair in-context examples with the given text prompts. We finetune the model from the first stage on three video generation tasks, incorporating multi-modal instructions.
  arXiv  Detail & Related papers  (2024-07-08T18:12:49Z)
• Learning Unseen Modality Interaction [54.23533023883659]
  Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. We pose the problem of unseen modality interaction and introduce a first solution. It exploits a module that projects the multidimensional features of different modalities into a common space with rich information preserved.
  arXiv  Detail & Related papers  (2023-06-22T10:53:10Z)
• Multilevel Hierarchical Network with Multiscale Sampling for Video Question Answering [16.449212284367366]
  We propose a novel Multilevel Hierarchical Network (MHN) with multiscale sampling for VideoQA. MHN comprises two modules, namely Recurrent Multimodal Interaction (RMI) and Parallel Visual Reasoning (PVR) With a multiscale sampling, RMI iterates the interaction of appearance-motion information at each scale and the question embeddings to build the multilevel question-guided visual representations. PVR infers the visual cues at each level in parallel to fit with answering different question types that may rely on the visual information at relevant levels.
  arXiv  Detail & Related papers  (2022-05-09T06:28:56Z)
• Attention Bottlenecks for Multimodal Fusion [90.75885715478054]
  Machine perception models are typically modality-specific and optimised for unimodal benchmarks. We introduce a novel transformer based architecture that uses fusion' for modality fusion at multiple layers. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks.
  arXiv  Detail & Related papers  (2021-06-30T22:44:12Z)
• Multi-modal Transformer for Video Retrieval [67.86763073161012]
  We present a multi-modal transformer to jointly encode the different modalities in video. On the natural language side, we investigate the best practices to jointly optimize the language embedding together with the multi-modal transformer. This novel framework allows us to establish state-of-the-art results for video retrieval on three datasets.
  arXiv  Detail & Related papers  (2020-07-21T07:38:46Z)
• Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers [89.00926092864368]
  We present a semantics-controlled multi-modal shuffled Transformer reasoning framework for the audio-visual scene aware dialog task. We also present a novel dynamic scene graph representation learning pipeline that consists of an intra-frame reasoning layer producing-semantic graph representations for every frame. Our results demonstrate state-of-the-art performances on all evaluation metrics.
  arXiv  Detail & Related papers  (2020-07-08T02:00:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.