Expressing an Image Stream with a Sequence of Natural Sentences

By Cesc Chunseong Park, Gunhee Kim. 2015

99 citations recorded by the source corpus.

Subfields: Natural Language Processing, 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 Natural Language Processing

1. Wei Xu
2. Haonan Yu
3. Douwe Kiela
4. Yi Yang
5. Barbara Plank
6. Mohit Bansal
7. Desmond Elliott
8. Qi Liu

In Multimodal Learning

1. Yi Yang
2. Wei Xu
3. Haonan Yu
4. Devi Parikh
5. Desmond Elliott
6. Zhiheng Huang
7. Nazli Ikizler-Cinbis
8. Aykut Erdem

Citations in the corpus

• The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes (2020, background): “[56] for a survey), with great progress on important problems such as visual question answering [3, 26] and image caption generation and retrieval [8, 88, 43, 68, 28], with offshoot tasks focusing specifically on visual reasoning [36], referring expressions [39], visual storytelling [57, 32], visual”
• Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks (2015, methodology): “oning method. The overall structure of an image captioner (instance-tosequence) is also usually simpler than that of a video captioner (sequence-to-sequence). Some other methods, such as Park and Kim [34], addressed the problem of retrieving sentences from training database to describe a sequence of”
• Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures (2016, methodology): “An interesting intermediate approach involves the annotation of image streams with sequences of sentences, see the work of Park and Kim (2015). category in Section 2.”
• Finding Similar Exercises in Online Education Systems (2018, background): “[27] developed a coherent recurrent convolutional network architecture to capture the associations between a sequence of images and sentences.”
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods (2019, unknown): “In contrast to videos, consecutive images in the streams can have sharp changes of visual content, which cause the abrupt discontinuity between consecutive sentences (Park & Kim, 2015).”
• Attend to You: Personalized Image Captioning with Context Sequence Memory Networks (2017, background): “[3, 22, 25, 28, 31, 33]), which predict a word at every time step, based on only a current input and a single or a few hidden states as an implicit summary of all previous history.”