Audio-visual Event Localization on Portrait Mode Short Videos

• URL: http://arxiv.org/abs/2504.06884v1
• Date: Wed, 09 Apr 2025 13:38:40 GMT
• Title: Audio-visual Event Localization on Portrait Mode Short Videos
• Authors: Wuyang Liu, Yi Chai, Yongpeng Yan, Yanzhen Ren,
• Abstract summary: We introduce AVE-PM, the first AVEL dataset specifically designed for portrait mode short videos.<n>State-of-the-art AVEL methods suffer an average 18.66% performance drop during cross-mode evaluation.<n>We investigate optimal preprocessing recipes and the impact of background music for AVEL on portrait mode videos.
• Score: 2.929891500796793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Audio-visual event localization (AVEL) plays a critical role in multimodal scene understanding. While existing datasets for AVEL predominantly comprise landscape-oriented long videos with clean and simple audio context, short videos have become the primary format of online video content due to the the proliferation of smartphones. Short videos are characterized by portrait-oriented framing and layered audio compositions (e.g., overlapping sound effects, voiceovers, and music), which brings unique challenges unaddressed by conventional methods. To this end, we introduce AVE-PM, the first AVEL dataset specifically designed for portrait mode short videos, comprising 25,335 clips that span 86 fine-grained categories with frame-level annotations. Beyond dataset creation, our empirical analysis shows that state-of-the-art AVEL methods suffer an average 18.66% performance drop during cross-mode evaluation. Further analysis reveals two key challenges of different video formats: 1) spatial bias from portrait-oriented framing introduces distinct domain priors, and 2) noisy audio composition compromise the reliability of audio modality. To address these issues, we investigate optimal preprocessing recipes and the impact of background music for AVEL on portrait mode videos. Experiments show that these methods can still benefit from tailored preprocessing and specialized model design, thus achieving improved performance. This work provides both a foundational benchmark and actionable insights for advancing AVEL research in the era of mobile-centric video content. Dataset and code will be released.

Related papers

• Aligned Better, Listen Better for Audio-Visual Large Language Models [21.525317311280205]
  Video inherently contains audio, which supplies information to vision. Video large language models (Video-LLMs) can encounter many audio-centric settings. Existing models exhibit deficiencies in exploiting audio information, leading to weak understanding and hallucinations.
  arXiv  Detail & Related papers  (2025-04-02T18:47:09Z)
• Multi-subject Open-set Personalization in Video Generation [110.02124633005516]
  We present Video Alchemist $-$ a video model with built-in multi-subject, open-set personalization capabilities.<n>Our model is built on a new Diffusion Transformer module that fuses each conditional reference image and its corresponding subject-level text prompt.<n>Our method significantly outperforms existing personalization methods in both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2025-01-10T18:59:54Z)
• MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions [69.9122231800796]
  We present MMTrail, a large-scale multi-modality video-language dataset incorporating more than 20M trailer clips with visual captions. We propose a systemic captioning framework, achieving various modality annotations with more than 27.1k hours of trailer videos. Our dataset potentially paves the path for fine-grained large multimodal-language model training.
  arXiv  Detail & Related papers  (2024-07-30T16:43:24Z)
• Text-to-feature diffusion for audio-visual few-shot learning [59.45164042078649]
  Few-shot learning from video data is a challenging and underexplored, yet much cheaper, setup. We introduce a unified audio-visual few-shot video classification benchmark on three datasets. We show that AV-DIFF obtains state-of-the-art performance on our proposed benchmark for audio-visual few-shot learning.
  arXiv  Detail & Related papers  (2023-09-07T17:30:36Z)
• Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model [70.97446870672069]
  Video anomaly detection (VAD) has been paid increasing attention due to its potential applications. Video Anomaly Retrieval ( VAR) aims to pragmatically retrieve relevant anomalous videos by cross-modalities. We present two benchmarks, UCFCrime-AR and XD-Violence, constructed on top of prevalent anomaly datasets.
  arXiv  Detail & Related papers  (2023-07-24T06:22:37Z)
• Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation [18.001730255429347]
  Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. We propose a new cost-effective strategy to build challenging and relatively unbiased high-quality audio-visual segmentation benchmarks. Experiments conducted on existing AVS datasets and on our new benchmark show that our method achieves state-of-the-art (SOTA) segmentation accuracy.
  arXiv  Detail & Related papers  (2023-04-06T09:54:06Z)
• Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline [53.07236039168652]
  We focus on the task of dense-localizing audio-visual events, which aims to jointly localize and recognize all audio-visual events occurring in an untrimmed video. We introduce the first Untrimmed Audio-Visual dataset, which contains 10K untrimmed videos with over 30K audio-visual events. Next, we formulate the task using a new learning-based framework, which is capable of fully integrating audio and visual modalities to localize audio-visual events with various lengths and capture dependencies between them in a single pass.
  arXiv  Detail & Related papers  (2023-03-22T22:00:17Z)
• Audio-Visual Segmentation [47.10873917119006]
  We propose to explore a new problem called audio-visual segmentation (AVS) The goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. We construct the first audio-visual segmentation benchmark (AVSBench), providing pixel-wise annotations for the sounding objects in audible videos.
  arXiv  Detail & Related papers  (2022-07-11T17:50:36Z)
• Localizing Visual Sounds the Hard Way [149.84890978170174]
  We train the network to explicitly discriminate challenging image fragments, even for images that do contain the object emitting the sound. We show that our algorithm achieves state-of-the-art performance on the popular Flickr SoundNet dataset. We introduce the VGG-Sound Source (VGG-SS) benchmark, a new set of annotations for the recently-introduced VGG-Sound dataset.
  arXiv  Detail & Related papers  (2021-04-06T17:38:18Z)

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.