Video Alignment

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

4 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 43 papers with code (83 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Time-Contrastive Networks: Self-Supervised Learning from Video
  23 Apr 2017 7 repositories listed
  While representations are learned from an unlabeled collection of task-related videos, robot behaviors such as pouring are learned by watching a single 3rd-person demonstration by a human.
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
  3 Dec 2024 2 repositories listed Syntology ran 18 of 27 samples · 9 unverified · 27 pointer-only (licence)
  In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models.
• VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment
  21 Aug 2024 2 repositories listed
  To the best of our knowledge, VE-Bench introduces the first quality assessment dataset for video editing and an effective subjective-aligned quantitative metric for this domain.
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
  12 Aug 2024 2 repositories listed Syntology ran 7 of 7 samples · 0 unverified
  We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos aligned with text prompt, with a frame rate of 16 fps and resolution of…
• MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions
  8 Jul 2024 2 repositories listed
  Sora's high-motion intensity and long consistent videos have significantly impacted the field of video generation, attracting unprecedented attention.
• AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI
  3 Jan 2024 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  To establish a unified evaluation framework for video generation tasks, our benchmark includes 11 metrics spanning four dimensions to assess algorithm performance.
• View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose
  23 Oct 2020 2 repositories listed
  Recognition of human poses and actions is crucial for autonomous systems to interact smoothly with people.
• View-Invariant Probabilistic Embedding for Human Pose
  2 Dec 2019 2 repositories listed
  Depictions of similar human body configurations can vary with changing viewpoints.
• Temporal Cycle-Consistency Learning
  16 Apr 2019 2 repositories listed Syntology ran 0 of 12 samples · 12 unverified
  We introduce a self-supervised representation learning method based on the task of temporal alignment between videos.
• Learning from Video and Text via Large-Scale Discriminative Clustering
  27 Jul 2017 2 repositories listed
  Discriminative clustering has been successfully applied to a number of weakly-supervised learning tasks.
• DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
  10 Jun 2025 1 repository listed Syntology ran 1 of 2 samples · 1 unverified
  The parameter-efficient adaptation of the image-text pretraining model CLIP for video-text retrieval is a prominent area of research.
• Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation
  29 May 2025 1 repository listed
  Generating highly dynamic and photorealistic portrait animations driven by audio and skeletal motion remains challenging due to the need for precise lip synchronization, natural facial expressions, and high-fidelity…
• LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation
  17 May 2025 1 repository listed
  To this end, we present AIGVE-60K, a comprehensive dataset and benchmark for AI-Generated Video Evaluation, which features (i) comprehensive tasks, encompassing 3, 050 extensive prompts across 20 fine-grained task…
• HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
  7 May 2025 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Customized video generation aims to produce videos featuring specific subjects under flexible user-defined conditions, yet existing methods often struggle with identity consistency and limited input modalities.
• Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization
  5 Apr 2025 1 repository listed
  With the ability of 4D and video generation, Video4DGen offers a powerful tool for applications in virtual reality, animation, and beyond.
• VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion
  11 Mar 2025 1 repository listed
  We propose a new task, video referring matting, which obtains the alpha matte of a specified instance by inputting a referring caption.
• Deep Understanding of Sign Language for Sign to Subtitle Alignment
  5 Mar 2025 1 repository listed
  The objective of this work is to align asynchronous subtitles in sign language videos with limited labelled data.
• Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
  31 Jan 2025 1 repository listed Syntology ran 7 of 10 samples · 3 unverified
  The remarkable progress in text-to-video diffusion models enables photorealistic generations, although the contents of the generated video often include unnatural movement or deformation, reverse playback, and…
• Sound Bridge: Associating Egocentric and Exocentric Videos via Audio Cues
  1 Jan 2025 1 repository listed
  However, existing visual-to-visual and visual-to-textual Ego-Exo video alignment methods struggle with the problem that there could be non-visual overlap for the same activity.
• Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification
  22 Nov 2024 1 repository listed
  As these models become prevalent, various metrics and benchmarks have emerged to evaluate the quality of the generated videos.
• T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design
  8 Oct 2024 1 repository listed Syntology ran 8 of 8 samples · 0 unverified · 8 pointer-only (licence)
  In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model.
• Mamba-Enhanced Text-Audio-Video Alignment Network for Emotion Recognition in Conversations
  8 Sep 2024 1 repository listed
  MaTAV is with the advantages of aligning unimodal features to ensure consistency across different modalities and handling long input sequences to better capture contextual multimodal information.
• Self-Supervised Contrastive Learning for Videos using Differentiable Local Alignment
  6 Sep 2024 1 repository listed
  Robust frame-wise embeddings are essential to perform video analysis and understanding tasks.
• FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds
  1 Jul 2024 1 repository listed Syntology ran 3 of 8 samples · 5 unverified
  Meanwhile, the temporal controller incorporates an onset detector and a timestampbased adapter to achieve precise audio-video alignment.
• SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
  20 Jun 2024 1 repository listed Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
  To mitigate the risk of harmful outputs from large vision models (LVMs), we introduce the SafeSora dataset to promote research on aligning text-to-video generation with human values.
• Listen Then See: Video Alignment with Speaker Attention
  21 Apr 2024 1 repository listed
  Our approach exhibits an improved ability to leverage the video modality by using the audio modality as a bridge with the language modality.
• Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment
  18 Mar 2024 1 repository listed Syntology ran 5 of 5 samples · 0 unverified · 5 pointer-only (licence)
  Based on T2VQA-DB, we propose a novel transformer-based model for subjective-aligned Text-to-Video Quality Assessment (T2VQA).
• CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility
  18 Mar 2024 1 repository listed
  To this end, this paper proposes a novel text-guided video inpainting model that achieves better consistency, controllability and compatibility.
• EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
  17 Oct 2023 1 repository listed Syntology ran 5 of 11 samples · 6 unverified · 11 pointer-only (licence)
  For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos.
• Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation
  27 Sep 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  In this paper, we are the first to propose a hybrid model, dubbed as Show-1, which marries pixel-based and latent-based VDMs for text-to-video generation.

Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.