Learning Language-Visual Embedding for Movie Understanding with Natural-Language

Abstract

Learning a joint language-visual embedding has a number of very appealing properties and can result in variety of practical application, including natural language image/video annotation and search. In this work, we study three different joint language-visual neural network model architectures. We evaluate our models on large scale LSMDC16 movie dataset for two tasks: 1) Standard Ranking for video annotation and retrieval 2) Our proposed movie multiple-choice test. This test facilitate automatic evaluation of visual-language models for natural language video annotation based on human activities. In addition to original Audio Description (AD) captions, provided as part of LSMDC16, we collected and will make available a) manually generated re-phrasings of those captions obtained using Amazon MTurk b) automatically generated human activity elements in "Predicate + Object" (PO) phrases based on "Knowlywood", an activity knowledge mining model. Our best model archives Recall@10 of 19.2% on annotation and 18.9% on video retrieval tasks for subset of 1000 samples. For multiple-choice test, our best model achieve accuracy 58.11% over whole LSMDC16 public test-set.

13 pages

References in corpus (11)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
• VQA: Visual Question Answering
• Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering
• Sequence to Sequence -- Video to Text
• Describing Videos by Exploiting Temporal Structure
• Ask Your Neurons: A Neural-based Approach to Answering Questions about Images
• Blocks and Fuel: Frameworks for deep learning
• Order-Embeddings of Images and Language
• Uncovering Temporal Context for Video Question and Answering

Cited by in corpus (18)

• HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
• Use What You Have: Video Retrieval Using Representations From Collaborative Experts
• Dual Encoding for Video Retrieval by Text
• Learning a Text-Video Embedding from Incomplete and Heterogeneous Data
• MDMMT: Multidomain Multimodal Transformer for Video Retrieval
• CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
• VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
• Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval
• MERLOT: Multimodal Neural Script Knowledge Models
• End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering
• Deep Multimodal Feature Encoding for Video Ordering
• VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
• TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment
• Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval
• SSAN: Separable Self-Attention Network for Video Representation Learning
• ActBERT: Learning Global-Local Video-Text Representations
• SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval
• VideoMCC: a New Benchmark for Video Comprehension