SeqBench: Benchmarking Sequential Narrative Generation in Text-to-Video Models

• URL: http://arxiv.org/abs/2510.13042v1
• Date: Tue, 14 Oct 2025 23:40:57 GMT
• Title: SeqBench: Benchmarking Sequential Narrative Generation in Text-to-Video Models
• Authors: Zhengxu Tang, Zizheng Wang, Luning Wang, Zitao Shuai, Chenhao Zhang, Siyu Qian, Yirui Wu, Bohao Wang, Haosong Rao, Zhenyu Yang, Chenwei Wu,
• Abstract summary: We present SeqBench, a comprehensive benchmark for evaluating sequential narrative coherence in T2V generation.<n>We use a dataset of 320 prompts spanning various narrative complexities, with 2,560 human-annotated videos generated from 8 state-of-the-art T2V models.<n>Our DTG-based metric demonstrates a strong correlation with human annotations.
• Score: 9.237220559112837
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-video (T2V) generation models have made significant progress in creating visually appealing videos. However, they struggle with generating coherent sequential narratives that require logical progression through multiple events. Existing T2V benchmarks primarily focus on visual quality metrics but fail to evaluate narrative coherence over extended sequences. To bridge this gap, we present SeqBench, a comprehensive benchmark for evaluating sequential narrative coherence in T2V generation. SeqBench includes a carefully designed dataset of 320 prompts spanning various narrative complexities, with 2,560 human-annotated videos generated from 8 state-of-the-art T2V models. Additionally, we design a Dynamic Temporal Graphs (DTG)-based automatic evaluation metric, which can efficiently capture long-range dependencies and temporal ordering while maintaining computational efficiency. Our DTG-based metric demonstrates a strong correlation with human annotations. Through systematic evaluation using SeqBench, we reveal critical limitations in current T2V models: failure to maintain consistent object states across multi-action sequences, physically implausible results in multi-object scenarios, and difficulties in preserving realistic timing and ordering relationships between sequential actions. SeqBench provides the first systematic framework for evaluating narrative coherence in T2V generation and offers concrete insights for improving sequential reasoning capabilities in future models. Please refer to https://videobench.github.io/SeqBench.github.io/ for more details.

Related papers

• SPATIALALIGN: Aligning Dynamic Spatial Relationships in Video Generation [37.165709423088266]
  Most text-to-video (T2V) generators prioritize aesthetic quality, but often ignore the spatial constraints in the generated videos.<n>We present SPATIALALIGN, a self-improvement framework that enhances T2V models capabilities to depict Dynamic Spatial Relationships (DSR) specified in text prompts.<n>Specifically, we design DSR-SCORE, a geometry-based metric that quantitatively measures the alignment between generated videos and the specified DSRs in prompts.
  arXiv  Detail & Related papers  (2026-02-26T08:34:09Z)
• Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs [54.502280390499756]
  We propose TimeWarp to create a targeted synthetic temporal dataset to fine-tune the model's responses to encourage it to focus on the given input video.<n>We demonstrate that when our method is applied to existing models, it significantly improves performance on temporal understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-04T21:48:40Z)
• VideoMolmo: Spatio-Temporal Grounding Meets Pointing [66.19964563104385]
  VideoMolmo is a model tailored for fine-grained pointing of video sequences.<n>A novel temporal mask fusion employs SAM2 for bidirectional point propagation.<n>To evaluate the generalization of VideoMolmo, we introduce VPoMolS-temporal, a challenging out-of-distribution benchmark spanning five real-world scenarios.
  arXiv  Detail & Related papers  (2025-06-05T17:59:29Z)
• TimeLogic: A Temporal Logic Benchmark for Video QA [64.32208175236323]
  We introduce the TimeLogic QA (TLQA) framework to automatically generate temporal logical questions.<n>We leverage 4 datasets, STAR, Breakfast, AGQA, and CrossTask, and generate 2k and 10k QA pairs for each category.<n>We assess the VideoQA model's temporal reasoning performance on 16 categories of temporal logic with varying temporal complexity.
  arXiv  Detail & Related papers  (2025-01-13T11:12:59Z)
• TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models [75.42002690128486]
  TemporalBench is a new benchmark dedicated to evaluating fine-grained temporal understanding in videos. It consists of 10K video question-answer pairs, derived from 2K high-quality human annotations detailing the temporal dynamics in video clips. Results show that state-of-the-art models like GPT-4o achieve only 38.5% question answering accuracy on TemporalBench.
  arXiv  Detail & Related papers  (2024-10-14T17:59:58Z)
• Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation [72.90144343056227]
  We explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We introduce a novel framework, termed "VD-IT", tailored with dedicatedly designed components built upon a fixed T2V model. Our VD-IT achieves highly competitive results, surpassing many existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-18T17:59:58Z)
• Temporally Consistent Transformers for Video Generation [80.45230642225913]
  To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. No established benchmarks on complex data exist for rigorously evaluating video generation with long temporal dependencies. We introduce the Temporally Consistent Transformer (TECO), a generative model that substantially improves long-term consistency while also reducing sampling time.
  arXiv  Detail & Related papers  (2022-10-05T17:15:10Z)
• Expressing Multivariate Time Series as Graphs with Time Series Attention Transformer [14.172091921813065]
  We propose the Time Series Attention Transformer (TSAT) for multivariate time series representation learning. Using TSAT, we represent both temporal information and inter-dependencies of time series in terms of edge-enhanced dynamic graphs. We show that TSAT clearly outerperforms six state-of-the-art baseline methods in various forecasting horizons.
  arXiv  Detail & Related papers  (2022-08-19T12:25:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.