VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations

• URL: http://arxiv.org/abs/2604.27259v1
• Date: Wed, 29 Apr 2026 23:17:33 GMT
• Title: VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations
• Abstract summary: We introduce VTBench, a framework that re-examines through multimodal fusion of raw sequences and chart-based visualizations.<n>We develop a modular architecture supporting multiple fusion strategies, including single-chart visual-numerical fusion, multi-chart visual fusion, and full multimodal fusion with raw inputs.
• Score: 11.42837813008733
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Time-series classification (TSC) has advanced significantly with deep learning, yet most models rely solely on raw numerical inputs, overlooking alternative representations. While texture-based encodings such as Gramian Angular Fields (GAF) and Recurrence Plots (RP) convert time series into 2D images, they often require heavy preprocessing and yield less intuitive representations. In contrast, chart-based visualizations offer more interpretable alternatives and show promise in specific domains; however, their effectiveness remains underexplored, with limited systematic evaluation across chart types, visual encoding choices, and datasets. In this work, we introduce VTBench, a systematic and extensible framework that re-examines TSC through multimodal fusion of raw sequences and chart-based visualizations. VTBench generates lightweight, human-interpretable plots -- line, area, bar, and scatter, providing complementary views of the same signal. We develop a modular architecture supporting multiple fusion strategies, including single-chart visual-numerical fusion, multi-chart visual fusion, and full multimodal fusion with raw inputs. Through experiments across 31 UCR datasets, we show that: (1) chart-only models are competitive in selected settings, particularly on smaller datasets; (2) combining multiple chart types can improve accuracy by capturing complementary visual cues; and (3) multimodal models improve or maintain performance when visual features provide non-redundant information, but may degrade accuracy when they introduce redundancy. We further distill practical guidelines for selecting chart types, fusion strategies, and configurations. VTBench establishes a unified foundation for interpretable and effective multimodal time-series classification.

Related papers

• BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning [51.472854950300416]
  We propose BigCharts, a dataset creation pipeline that generates visually diverse chart images.<n>Unlike purely synthetic datasets, BigCharts incorporates real-world data, ensuring authenticity and visual diversity.<n>By introducing novel reward signals specifically designed for chart reasoning, our approach enhances model robustness and generalization.
  arXiv  Detail & Related papers  (2025-08-13T13:39:17Z)
• Socratic Chart: Cooperating Multiple Agents for Robust SVG Chart Understanding [14.75820681491341]
  Existing benchmarks reveal reliance on text-based shortcuts and probabilistic pattern-matching rather than genuine visual reasoning.<n>We propose Socratic Chart, a new framework that transforms chart images into Scalable Vector Graphics representations.<n>Our framework surpasses state-of-the-art models in accurately capturing chart primitives and improving reasoning performance.
  arXiv  Detail & Related papers  (2025-04-14T00:07:39Z)
• Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement [16.22363384653305]
  Multimodal Large Language Models (MLLMs) perform fine-grained visual parsing, precise code synthesis, and robust cross-modal reasoning.<n>We propose a dual preference-guided refinement framework that combines a feedback-driven, dual-modality reward mechanism with iterative preference learning.<n>Our framework significantly enhances the performance of general-purpose open-source MLLMs, enabling them to generate high-quality plotting code.
  arXiv  Detail & Related papers  (2025-04-03T07:51:20Z)
• RefChartQA: Grounding Visual Answer on Chart Images through Instruction Tuning [63.599057862999]
  RefChartQA is a novel benchmark that integrates Chart Question Answering (ChartQA) with visual grounding.<n>Our experiments demonstrate that incorporating spatial awareness via grounding improves response accuracy by over 15%.
  arXiv  Detail & Related papers  (2025-03-29T15:50:08Z)
• Graph-Based Multimodal Contrastive Learning for Chart Question Answering [11.828192162922436]
  This work introduces a novel joint multimodal scene graph framework that explicitly models the relationships among chart components and their underlying structures.<n>The framework integrates both visual and textual graphs to capture structural and semantic characteristics.<n>A graph contrastive learning strategy aligns node representations across modalities enabling their seamless incorporation into a transformer decoder as soft prompts.
  arXiv  Detail & Related papers  (2025-01-08T06:27:07Z)
• Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation [61.91492500828508]
  Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal support samples.<n>We introduce a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality.<n>We propose a simple yet effective Test-time Adaptive Cross-modal (TACC) technique to mitigate training bias.
  arXiv  Detail & Related papers  (2024-10-29T19:28:41Z)
• On Pre-training of Multimodal Language Models Customized for Chart Understanding [83.99377088129282]
  This paper explores the training processes necessary to improve MLLMs' comprehension of charts.<n>We introduce CHOPINLLM, an MLLM tailored for in-depth chart comprehension.
  arXiv  Detail & Related papers  (2024-07-19T17:58:36Z)
• Fast Multi-view Clustering via Ensembles: Towards Scalability, Superiority, and Simplicity [63.85428043085567]
  We propose a fast multi-view clustering via ensembles (FastMICE) approach. The concept of random view groups is presented to capture the versatile view-wise relationships. FastMICE has almost linear time and space complexity, and is free of dataset-specific tuning.
  arXiv  Detail & Related papers  (2022-03-22T09:51:24Z)
• Consistent Multiple Graph Embedding for Multi-View Clustering [41.17336912278538]
  We propose a novel Consistent Multiple Graph Embedding Clustering framework(CMGEC) Specifically, a multiple graph auto-encoder is designed to flexibly encode the complementary information of multi-view data. To guide the learned common representation maintaining the similarity of the neighboring characteristics in each view, a Multi-view Mutual Information Maximization module(MMIM) is introduced.
  arXiv  Detail & Related papers  (2021-05-11T09:08:22Z)
• Multi-view Graph Learning by Joint Modeling of Consistency and Inconsistency [65.76554214664101]
  Graph learning has emerged as a promising technique for multi-view clustering with its ability to learn a unified and robust graph from multiple views. We propose a new multi-view graph learning framework, which for the first time simultaneously models multi-view consistency and multi-view inconsistency in a unified objective function. Experiments on twelve multi-view datasets have demonstrated the robustness and efficiency of the proposed approach.
  arXiv  Detail & Related papers  (2020-08-24T06:11:29Z)

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.