Challenge: Existing video QA datasets only contain QA pairs without labels for key clips or regions needed to answer the question.
Approach: They propose a framework that grounds evidence in both spatial and temporal domains to answer questions about videos using bounding boxes.
Outcome: The proposed framework can produce interpretable spatio-temporal attention visualizations.

Similar Papers

VideoQA-TA: Temporal-Aware Multi-Modal Video Question Answering (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for video question answering align visual or textual features directly with large language models, limiting the deep semantic association between modalities and hindering a comprehensive understanding of interactions within spatial and temporal contexts.
Approach: They propose a temporal-aware framework for multi-modal video question answering that aligns videos and questions at fine-grained levels.
Outcome: The proposed framework improves reasoning ability and accuracy of videoQA by aligning videos and questions at fine-grained levels.
Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA (2020.acl-main)

Copied to clipboard

Challenge: Recent years have witnessed a paradigm shift in the way we get our information, and a lot of it.
Approach: They propose a video question answering model which integrates multi-modal input sources and finds temporally relevant information to answer questions.
Outcome: The proposed model outperforms the state-of-the-art on a TVQA dataset.
TVQA: Localized, Compositional Video Question Answering (D18-1)

Copied to clipboard

Challenge: Recent studies have focused on image-based question-answering (QA) tasks, but little has been done on video-based QA.
Approach: They present a large-scale video QA dataset based on 6 popular TV shows . they provide analysis of the new dataset and trainable neural network framework .
Outcome: The proposed dataset includes 152,545 QA pairs from 21,793 clips spanning over 460 hours of video.
Video Question Answering: Datasets, Algorithms and Challenges (2022.emnlp-main)

Copied to clipboard

Challenge: Recent advances in video question answering have led to a surge in popularity . despite the popularity, VideoQA remains one of the greatest challenges .
Approach: They categorize the video question-answer datasets into normal VideoQA, multi-modal VideoQA and knowledge-based VideoQA according to the modalities invoked in the question-announcement pairs.
Outcome: The proposed methods are mainly designed for Factoid QA and inference VideoQA . the proposed methods have been compared with other methods and are robust and interpretable.
Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamic Audio-Visual Scenarios (2023.findings-emnlp)

Copied to clipboard

Challenge: Audio-visual question answering requires multistep spatio-temporal reasoning over multimodal contexts.
Approach: They propose a new target-aware joint spatio-temporal grounding network for audio-visual question answering . the proposed system integrates audio-vision fusion and question-awful temporal grounding into one module .
Outcome: The proposed method over existing state-of-the-art methods is effective over existing methods . it can focus on audio-visual cues relevant to the query subject by utilizing explicit semantics from the question .
Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video (P19-1)

Copied to clipboard

Challenge: Existing techniques for weakly-supervised spatio-temporally grounding natural sentence in video are lacking .
Approach: They propose a weakly-supervised task for spatially grounding sentences in video . they extract instances from video and encode them using attentive interactor . results demonstrate superiority of their proposed task over baseline approaches .
Outcome: The proposed model outperforms baseline approaches in a weakly-supervised task . it can characterize reliable instance-sentence pairs and penalize unreliable ones .
BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to video-grounded dialogues focus on superficial temporal-level visual cues, but neglect more fine-grained spatial signals from videos.
Approach: They propose a vision-language neural framework for high-resolution queries in videos based on textual cues that exploits both spatial and temporal-level information.
Outcome: The proposed approach outperforms previous approaches on the TGIF-QA benchmark and significantly outperformed previous approaches.
Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement (2025.acl-long)

Copied to clipboard

Challenge: Existing time series models focus on a narrow spectrum of tasks, such as forecasting or anomaly detection.
Approach: They propose a framework that enables natural language queries across multiple time series tasks such as numerical analytical tasks and open-ended question answering with reasoning.
Outcome: The proposed framework enables natural language queries across multiple time series tasks and allows for more advanced and intuitive interactions with temporal data.
ComplexTempQA: A 100m Dataset for Complex Temporal Question Answering (2025.emnlp-main)

Copied to clipboard

Challenge: Existing datasets that focus on temporal knowledge are limited in size and lack comprehensive coverage of temporal information.
Approach: They introduce a large-scale temporal question-answer-matching dataset . the new taxonomy categorizes questions as attributes, comparisons, and counting questions .
Outcome: The proposed dataset surpasses existing benchmarks in scale and scope.
MESAQA: A Dataset for Multi-Span Contextual and Evidence-Grounded Question Answering (2025.coling-main)

Copied to clipboard

Challenge: Existing question answering systems focus on extracting answers from single spans, but real-world scenarios require synthesizing information from multiple spans.
Approach: They propose a dataset that leverages the MASH-QA dataset and large language models (LLMs) to ensure that each Q/A pair requires considering all selected spans.
Outcome: The proposed method enables the model to answer multiple Q/A pairs in a single span, while ensuring that all selected spans are considered.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations