Pith. sign in

REVIEW 5 cited by

Temporal Convolutional Networks for Action Segmentation and Detection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1611.05267 v1 pith:EMMGIVJV submitted 2016-11-16 cs.CV

classification cs.CV
keywords temporalactionfine-grainednetworksconvolutionalconvolutionsdetectiondilated
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond. Typical approaches decouple this problem by first extracting local spatiotemporal features from video frames and then feeding them into a temporal classifier that captures high-level temporal patterns. We introduce a new class of temporal models, which we call Temporal Convolutional Networks (TCNs), that use a hierarchy of temporal convolutions to perform fine-grained action segmentation or detection. Our Encoder-Decoder TCN uses pooling and upsampling to efficiently capture long-range temporal patterns whereas our Dilated TCN uses dilated convolutions. We show that TCNs are capable of capturing action compositions, segment durations, and long-range dependencies, and are over a magnitude faster to train than competing LSTM-based Recurrent Neural Networks. We apply these models to three challenging fine-grained datasets and show large improvements over the state of the art.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection

    cs.LG 2026-03 conditional novelty 6.0 of 10

    Predicting multi-head attention queries from history and scoring cosine mismatch against an EMA target, combined with reconstruction error, improves unsupervised multivariate anomaly ranking and localization.

  2. Multi-Task Gaussian Processes and Dilated Convolutional Networks for Reconstruction of Reproductive Hormonal Dynamics

    cs.LG 2019-08 conditional novelty 6.0 of 10

    A multi-task Gaussian process plus a dilated convolutional network reconstructs daily hormone levels from sparse samples, and an oracle-style sampling rule is shown to help, all on synthetic cycles.

  3. Exploiting Temporality for Semi-Supervised Video Segmentation

    cs.CV 2019-08 conditional novelty 5.0 of 10

    Placing temporal modules inside the encoder of a U-Net, and propagating their outputs to the next convolutional blocks, improves semi-supervised video segmentation on CityScapes by about 6 mIoU points over a frame-by-...

  4. QuChaTeR: A Hybrid Quantum-Chaotic Temporal Framework for Earthquake Prediction

    cs.LG 2026-05 unverdicted novelty 4.0 of 10

    QuChaTeR hybridizes chaotic maps and variational quantum circuits with recurrent networks and wavelets to achieve faster convergence and better performance than classical and quantum-inspired baselines on real seismic...

  5. Hardware-Agnostic Modeling of Quantum Side-Channel Leakage via Conditional Dynamics and Learning from Full Correlation Data

    quant-ph 2026-02 reject novelty 4.0 of 10

    For a controlled-rotation probe, gate-sequence leakage is predicted to peak at θ*(k)=2 arcsin(√(2/(k+2))), but the paper provides neither a derivation of the envelope nor the experimental data supporting the prediction.

Pith tools