paper-with-me

Papers

Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding

2023-09-20 · Mohamed Afham, Satya Narayan Shukla, Omid Poursaeed, Pengchuan Zhang, Ashish Shah, SerNam Lim

While most modern video understanding models operate on short-range clips, real-world videos are often several minutes long with semantically consistent segments of variable length. A common approach to process long videos is applying a short-form video model over uniformly sampled clips of fixed temporal length and aggregating the outputs. This approach neglects the underlying nature of long videos since fixed-length clips are often redundant or uninformative. In this paper, we aim to provide a generic and adaptive sampling approach for long-form videos in lieu of the de facto uniform sampling. Viewing videos as semantically consistent segments, we formulate a task-agnostic, unsupervised, and scalable approach based on Kernel Temporal Segmentation (KTS) for sampling and tokenizing long videos. We evaluate our method on long-form video understanding tasks such as video classification and temporal action localization, showing consistent gains over existing approaches and achieving state-of-the-art performance on long-form video modeling.

📄 PDF Abstract BibTeX arXiv:2309.11569

Code (0)

등록된 구현이 없습니다.

Tasks

Action LocalizationFormTemporal Action LocalizationVideo ClassificationVideo Understanding

Similar Papers 제목 키워드 기반

NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models

2025-10-15 · Konstantinos Barmpas, Na Lee, Dimitrios Chalatsis, William Raftery 외 arxiv

Biosignals such as electroencephalography (EEG), electrocardiography (ECG), and electromyography (EMG) encode physiological activity across multiple temporal and spectral scales, yielding representations that are rich bu…

ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer

2026-03-03 · Chunyuan Deng, Sanket Lokegaonkar, Colin Lockard, Besnik Fetahu 외 arxiv

Modern language models still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level of granularity, which often leads to brittle and counterintuitive be…

Adaptive Active Contour Model for Brain Tumor Segmentation

2022-07-22 · International Journal of Computer Vision and Image Processing (IJCVIP) 12(1) 2022 7 · Gunjan Naik, Aditya Abhyankar, Bhushan Garware, Shubhangi kelkar

For accurately diagnosing the severity of brain tumors in MRI images, Glioma segmentation is a significant step. The Glioma segmentation is due to noise and weak edges of organs in medical images. The geodesic active con…

Brain Tumor SegmentationEdge DetectionImage Segmentationmodel+2

ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation

2025-05-22 · Lingfeng Wang, Hualing Lin, Senda Chen, Tao Wang 외

While humans effortlessly draw visual objects and shapes by adaptively allocating attention based on their complexity, existing multimodal large language models (MLLMs) remain constrained by rigid token representations. …

Chunking

From Smør-re-brød to Subwords: Training LLMs on Danish, One Morpheme at a Time

2025-04-02 · Mikkel Wildner Kildeberg, Emil Allerslev Schledermann, Nicolaj Larsen, Rob van der Goot

The best performing transformer-based language models use subword tokenization techniques, such as Byte-Pair-Encoding (BPE). However, these approaches often overlook linguistic principles, such as morphological segmentat…

Segmentation