Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Action LocalizationFormTemporal Action LocalizationVideo ClassificationVideo UnderstandingSimilar Papers 제목 키워드 기반
NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models
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
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
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+2ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
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. …
ChunkingFrom Smør-re-brød to Subwords: Training LLMs on Danish, One Morpheme at a Time
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