SV-TAD introduces native sparse 2D convolutions to enable convolutional adapters to operate directly on dynamically pruned token sets, addressing the inefficiency of dense reconstruction in token‑selection methods. By integrating this primitive into a temporal action detection framework, the approach cuts VideoMAEv2‑L computation by up to 64% and achieves 2.2× faster inference while preserving state‑of‑the‑art accuracy on THUMOS‑14 and ActivityNet‑1.3. When applied to InternVideoNext‑L, it surpasses prior state‑of‑the‑art performance at roughly half the computational cost and naturally supports auxiliary task tokens for improved fine‑grained assembly detection on ATTACH.
By Ricardo Pizarro, Roberto Valle, Jos\'e M. Buenaposada, Luis M. Bergasa, Luis Baumela
SV‑TAD introduces native sparse 2D convolutions to enable convolutional adapters to operate directly on dynamically pruned token sets, addressing the inefficiency of existing adapters that do not reduce inference‑time computation. By integrating this primitive, SV‑TAD cuts VideoMAEv2‑L computation by up to 64% and achieves 2.2× faster inference while preserving state‑of‑the‑art accuracy on THUMOS‑14 and ActivityNet‑1.3. When applied to InternVideoNext‑L, the approach surpasses prior state‑of‑the‑art performance at roughly half the computational cost and also supports auxiliary task tokens, improving fine‑grained assembly detection on ATTACH.
arXiv:2607. 03131v1 Announce Type: cross Abstract: Modern video surveillance systems generate far more video streams than human operators can effectively monitor, making automated analysis essential for timely detection of security events.
By Estera Dumitru, Stelian Sp\^inu
Precise Event Spotting (PES) requires distinguishing visually similar yet semantically distinct adjacent frames, making it fundamentally different from image classification and coarse action recognition. Although self-distillation methods such as DINO have shown strong representation learning ability in images, we find that directly applying them to PES is ineffective: without supervised guidance, subtle but crucial motion cues are often suppressed as noise, leading to representations that are insensitive to precise event boundaries.
The paper introduces a confidence‑normalized continuous multi‑timescale representation for event cameras, using logarithmic B‑spline temporal encoding and a geometry‑aware local confidence mechanism. When paired with a fixed feed‑forward EventCenterNet detector, this representation outperforms the compact CSTR representation on the PEDRo and Gen1 datasets. Additionally, a recursive exponential‑polynomial approximation is proposed to allow efficient event‑by‑event updates while maintaining detection performance.
By Fredrik Lundell, Per-Erik Forssen, M{\aa}rten Wadenb\"ack, Astrid Lundmark
arXiv:2510.26614v2 Announce Type: replace
Abstract: We propose tokenization of events and present a tokenizer, Spiking Patches, specifically designed for event cameras. Given a stream of asynchronous...
By Christoffer Koo {\O}hrstr{\o}m, Ronja G\"uldenring, Lazaros Nalpantidis
arXiv:2609.24031v1 Announce Type: new
Abstract: In recent years, pre-training has become fundamental to learning effective video representations, enabling strong transfer to downstream tasks. A popul...
By Akash Abdu Jyothi, Greg Mori
arXiv:2609.40347v1 Announce Type: new
Abstract: We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of r...
By Owais Iqbal, Sudipta Sarkar, Shyam Marjit, Omprakash Chakraborty, Anirban Chakraborty, Abir Das
The paper introduces SCARF, a real‑time velocity‑invariant representation for event cameras that preserves raw events while handling fast motion, stationary scenes, and independently moving objects. Unlike previous methods that convert events into image‑like forms and lose temporal detail, SCARF maintains temporal information and achieves state‑of‑the‑art performance in computational efficiency and representation quality.
By Mikihiro Ikura, Luna Gava, Jiahang Wu, Chiara Bartolozzi, Arren Glover
The paper proposes a confidence‑normalized continuous multi‑timescale event representation that encodes temporal information directly into event data using logarithmic B‑spline temporal encoding and a geometry‑aware local confidence mechanism. When applied to a fixed feed‑forward EventCenterNet detector, this representation outperforms the compact CSTR representation on the PEDRo and Gen1 datasets. Additionally, a recursive exponential‑polynomial approximation is introduced to allow efficient event‑by‑event updates while largely preserving detection performance.
arXiv:2505.01583v2 Announce Type: replace
Abstract: Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models (VLM...
By Jen-Hao Cheng, Yi-Hao Peng, Huapeng Zhou, Vivian Wang, Huayu Wang, Hsiang-Wei Huang, Wenhao Chai, Hou-I Liu, Kuang-Ming Chen, Cheng-Yen Yang, Yi-Ling Chen, Vibhav Vineet, Qin Cai, Jenq-Neng Hwang
arXiv:2606. 14724v1 Announce Type: cross Abstract: Video anomaly detection in surveillance settings must balance detection accuracy against real-time throughput, a tension that existing methods address either through stronger feature extractors or more efficient architectures, but rarely both.
By Xinze Zhang