Object Relational Graph With Teacher-Recommended Learning for Video Captioning

By Ziqi Zhang, Yaya Shi, Chunfen Yuan, Bing Li, Peijin Wang, Weiming Hu, Zhengjun Zha. 2020

316 citations recorded by the source corpus.

Taking full advantage of the information from both vision and language is critical for the video captioning task. Existing models lack adequate visual representation due to the neglect of interaction between object, and sufficient training for content-related words due to long-tailed problems. In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy. Specifically, we propose an object relational graph (ORG) based encoder, which captures more detailed interaction features to enrich visual representation. Meanwhile, we design a teacher-recommended learning (TRL) method to make full use of the successful external language model (ELM) to integrate the abundant linguistic knowledge into the caption model. The ELM generates more semantically similar word proposals which extend the groundtruth words used for training to deal with the long-tailed problem. Experimental evaluations on three benchmarks: MSVD, MSR-VTT and VATEX show the proposed ORG-TRL system achieves state-of-the-art performance. Extensive ablation studies and visualizations illustrate the effectiveness of our system.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Multimodal Learning

Citations in the corpus

GIT: A Generative Image-to-text Transformer for Vision and Language (2022, background): “[129] Ziqi Zhang, Yaya Shi, Chunfeng Yuan, Bing Li, Peijin Wang, Weiming Hu, and Zheng-Jun Zha.”
Open-book Video Captioning with Retrieve-Copy-Generate Network (2021, methodology): “With the advent of the encoder-decoder framework, most of the current work is studying how to better use visual features [35, 23, 1, 36, 22, 24] and design elaborate models [34, 2, 28, 13] to generate sentences directly.”
TransVG: End-to-End Visual Grounding with Transformers (2021, background): “Multi-modal fusion and reasoning is widely studied in the literature [1, 35, 49, 54, 65], and it is the core problem in visual grounding.”
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks (2020, background): “[296] leveraged the object-level information (teacher) to learn the scene feature representation (student) via a spatio-temporal graph.”
Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning (2023, background): “[126] Ziqi Zhang, Yaya Shi, Chunfeng Yuan, Bing Li, Peijin Wang, Weiming Hu, and Zheng-Jun Zha.”