The paper evaluates event-triggered recording strategies for static surveillance cameras, comparing six motion-based triggers, a CNN detector, strided detection, and hybrid approaches on a benchmark of seven scenes. Detector-based triggers reduce idle frame storage to 19‑28% versus 36‑89% for motion triggers, and remain robust under camera jitter, keeping under 29% idle frames. In addition, the study shows that increasing YOLO11n input resolution improves detection accuracy more than larger models, and that longer track memory boosts tracking IDF1, though detection remains the limiting factor.
By Shahran Rahman Alve
arXiv:2507.01927v3 Announce Type: replace
Abstract: While CNNs and ViTs dominate vision architectures, all-MLP models offer a structurally simpler alternative whose patch-independent processing is na...
By Zhentan Zheng
The paper investigates how knowledge distillation from event cameras to RGB images can alter the inductive biases of convolutional neural networks. By transferring learning from the event domain, the authors find that models gain color invariance, a shape bias, and improved robustness to high‑frequency noise, largely due to reduced reliance on texture and increased emphasis on edge‑based object shape. These changes are evidenced by early‑layer processing differences and a spectral trade‑off between robustness to missing high‑frequency content and vulnerability to its contamination or geometric disruption.
By Soshun Kihara, Shunsuke Yasuki, Masato Taki
The paper introduces ETHEREAL, the first accelerator for event-driven graph neural networks (EV‑GNNs) that can handle 640×480 resolution inputs. It achieves this through a neighbor‑parallel spline convolution engine and a 2D/3D‑split memory hierarchy that includes a novel region‑of‑interest spatiotemporal caching mechanism. Measurements show end‑to‑end inference latency of 25.6 µs and energy consumption of 1.7 µJ per event on state‑of‑the‑art workloads.
By Adrian Kneip, Martin Lefebvre, Daniel Gehrig, Victoria Catal\'an Pastor, Davide Scaramuzza, Marian Verhelst, Charlotte Frenkel
arXiv:2610. 39676v1 Announce Type: cross Abstract: Event cameras offer microsecond temporal resolution, high dynamic range and no motion blur, but referring video object segmentation (RVOS) lacks event-stream datasets and models.
By Sergei Fedorchenko, Max Zehnder, Nikola Zubi\'c, Rong Zou, Davide Scaramuzza
arXiv:2610.09873v1 Announce Type: new
Abstract: Binary Neural Networks (BNNs) enable efficient deep learning deployment on resource constrained devices with weights and activations compressed to one...
By Paul Longour, Julien Moreau, Franck Davoine
arXiv:2610.19624v1 Announce Type: new
Abstract: Visual recognition models usually process a fixed view under a fixed computation budget, although images often benefit from different scales and amount...
By Dikai Li, Weijia Wang, Yuan-Gen Wang
The paper evaluates how readout settings and operating points affect event-stream candidate selection in event-triggered recording. Using 520 DailyDVS‑200 clips and 47 participants, the authors compare several encoder configurations—including DINO‑CLS, patch mean, and MobileNetV3‑Small—across different accumulation durations and view counts, reporting metrics such as target capture, false triggers, and partial AUC. The study finds that lightweight baselines and specific operating points significantly influence performance, while no clear advantage is observed for the JEPA‑specific method.
By Yifan Shuai
arXiv:2607. 06922v1 Announce Type: new Abstract: Deep learning applications have been widely adopted on edge devices, to mitigate the privacy and latency issues of accessing cloud servers.
By Shuo Huai, Di Liu, Hao Kong, Weichen Liu, Ravi Subramaniam, Christian Makaya, Qian Lin
The paper presents an end‑to‑end system that converts driving footage into dynamic vision sensor (DVS) event streams, augments training with simulated DVS data, and trains a convolutional spiking neural network (Conv‑SNN) to classify pedestrian crossing intent as crossing or non‑crossing. The Conv‑SNN, trained with a class‑balanced loss and surrogate‑gradient learning, achieves high accuracy and F1 scores on JAAD and CARLA DVS datasets, outperforming or matching prior frame‑based methods while operating on sparse temporal representations. The study details architectural choices, neuron dynamics, and training protocols, and provides a convergence analysis and domain‑transfer evaluation.
By Henok Teklu, Mustafa Sakhai, Maciej Wielgosz, Matej Mertik
TT-VidT is a video pretraining method that decouples the temporal axis by combining a per‑frame ViT-B/16 spatial encoder with a compact Temporal Transfer Layer trained via Diff Compression. The authors conduct a systematic 24‑configuration study to isolate architecture, objective, and decoder effects, showing that the full TT-VidT design yields the strongest motion‑sensitive representations. In downstream fine‑tuning, TT‑VidT outperforms state‑of‑the‑art baselines on Jester, Something‑Something V2, ARID, and Diving48 while using significantly fewer encoder FLOPs.
By Shih-Ying Yeh, Daniel Z. Kaplan, Xuehai Wang, Fu-En Yang, Min-Hung Chen, Shang-Hong Lai
LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.
By Lukas Kuhn, Lucas Maes, Giuseppe Serra, Quentin Le Lidec, Yann LeCun, Randall Balestriero, Florian Buettner