Uncovering the Temporal Context for Video Question Answering

By Linchao Zhu, Zhongwen Xu, Yi Yang, Alexander G. Hauptmann. 2017

187 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Question Answering & Reading Comprehension

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 Question Answering & Reading Comprehension

Citations in the corpus

NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (2021, background): “Early VideoQA benchmarks [31, 51, 53, 54, 59, 64] rely on video descriptions [27, 52] (e.”
ActBERT: Learning Global-Local Video-Text Representations (2020, background): “, video question answering [36, 10, 18, 54], video captioning [46, 52], textvideo retrieval [47, 41, 25], video grounding [50].”
TVQA: Localized, Compositional Video Question Answering (2018, neutral): “Visual Question Answering: Several image-based VQA datasets have recently been constructed, e.g., DAQUAR (Malinowski and Fritz, 2014), VQA (Antol et al., 2015), COCO-Q (Ren et al., 2015a), FM-IQA (Gao et al., 2015), Visual Madlibs (Yu et al., 2015), Visual7W (Zhu et al., 2016), CLEVR (Johnson et al.”
Hierarchical Conditional Relation Networks for Video Question Answering (2020, methodology): “Spatio-temporal video representation is traditionally done by variations of recurrent networks (RNNs) among which many were used for VideoQA such as recurrent encoder-decoder [49, 47], bidirectional LSTM [15] and twostaged LSTM [44].”
Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning (2017, background): “…2015), visual dialog (Das et al., 2017; De Vries et al., 2017), visual question answering (Antol et al., 2015; Fukui et al., 2016; Lu et al., 2016; Zhu et al., 2017), visual story-telling (Huang et al., 2016), natural question generation (Mostafazadeh et al., 2017, 2016), and image generation…”
Watching a Small Portion could be as Good as Watching All: Towards Efficient Video Classification (2018, methodology): “Video classiﬁcation model generates representations which are usually beneﬁcial to other video analysis tasks, i.e. , video captioning [Pan et al. , 2016] and video question answering [Zhu et al. , 2017].”
Challenges and Prospects in Vision and Language Research (2019, background): “Video Question Answering has the additional requirement of understanding temporal dynamics (Zhao et al., 2017b; Zhu et al., 2017).”
Spatiotemporal-Textual Co-Attention Network for Video Question Answering (2019, methodology): “Some methods proposed temporal visual attention models [9, 45, 59] or spatio-temporal visual attention models [9, 14, 57, 58, 61] to select the potentially critical frames or the patches of interest in the video frames relevant to a question.”
LifeQA: A Real-life Dataset for Video Question Answering (2020, methodology): “VCQA (Zhu et al., 2017) consists of cooking and in-the-wild YouTube videos (about half of the dataset), and clips from movies (the other half).”
Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation (2019, background): “, Embodied Question Answering [8] and exploit temporal information for feature adaptation [39, 46, 7] and feature analysis [6].”
Recent Advances in Video Question Answering: A Review of Datasets and Methods (2021, methodology): “As an improvement over the model proposed by [1], [3] proposes a flexible encoder-decoder architecture using RNN, which covers a wide range of temporal information.”
Open-Ended Video Question Answering via Multi-Modal Conditional Adversarial Networks (2020, methodology): “approaches [45], [46] fill the missing words in the textual video description by ranking the candidate answers based on both visual content and contextual text description.”
Audio Visual Scene-Aware Dialog (2019, background): “ objects and the actions. It also expresses the spatio-temporal relationship between the dynamics in the scene [12,29,38]. Several datasets have been introduced to benchmark the video captioning task [15,19,22,35,41]. Visual Question Answering: Inspired by the success of image-based question answeri”
Modality Shifting Attention Network for Multi-Modal Video Question Answering (2020, background): “Video Question Answering (VideoQA) [38, 12] is a natural extension of VQA into the video domain.”
BERT Representations for Video Question Answering (2020, background): “…a video question answering framework that requires to simultaneously retrieve the relevant moments and referenced visual concepts is proposed; in [49] video-QA is studied in the temporal domain to do inference and prediction; and in [47] a scalable approach to automatically harvest videos and…”
Video Question Answering with Spatio-Temporal Reasoning (2019, methodology): “Most existing approaches make use of pooling, attention, reconstruction, and memory modules to learn the video features and to answer questions, e.g., Tapaswi et al. (2016), Yu et al. (2017), Zhu et al. (2017), Na et al. (2018), Gao and Ge (2018).”
Entangled Transformer for Image Captioning (2019, background): “Image captioning [39, 18] is one of the essential tasks [4, 39, 47] that attempts to break the semantic gap between vision and language.”
Multi-interaction Network with Object Relation for Video Question Answering (2019, methodology): “Temporal attention mechanism [11, 44] is one of the most commonly used technique.”