Selective Event Evidence and Persistent Temporal Priors (SEPT) is an event‑only framework designed to track points over long sequences by selectively weighting informative event evidence and maintaining trajectory constraints across overlapping temporal windows. It introduces Task‑Adaptive Event Evidence Modulation (TEEM), which learns a reliability field to weight the event tensor before feature extraction, and Persistent Trajectory Prior (PTP), which propagates geometric information using a local quadratic trajectory model with visibility‑aware corrections. Trained solely on synthetic EventKubric data, SEPT outperforms the retrained ETAP baseline and several event‑plus‑frame methods on multiple TAP and feature‑tracking datasets, with source code publicly available.
By Xiaokai Song, Zhang Li, Leqi Liu, Yibin Ye, Kun Wang, Xichao Teng
Event cameras offer microsecond-level temporal resolution and high dynamic range for low-altitude UAV perception. However, long-range UAVs often produce sparse, fragmented, and noise-contaminated event responses, where one semantic target may appear as multiple spatially separated blobs.
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
The paper introduces Spatially‑Sparse Linear Attention (SSLA), a novel attention mechanism that activates only a sparse subset of spatial states, enabling efficient parallel training and inference for event‑based vision. Building on SSLA, the authors present SSLA‑Det, an end‑to‑end asynchronous linear attention model that achieves state‑of‑the‑art accuracy on Gen1 and N‑Caltech101 while reducing per‑event computation by more than 20× compared to the strongest prior asynchronous baseline.
By Haiqing Hao, Zhipeng Sui, Rong Zou, Zijia Dai, Nikola Zubi\'c, Davide Scaramuzza, Wenhui Wang
FLEET is a token‑based feature extractor that processes event camera data directly, using random Fourier features and cross‑attention to compress variable‑length event streams into fixed‑size latent representations. By decoupling inference cost from sensor resolution, it avoids the high compute and temporal blurring associated with CNN‑based grid aggregation. Experiments on a new high‑throughput benchmark show that FLEET outperforms state‑of‑the‑art methods and remains robust across different observation frequencies.
By Tristan Gottwald, Maximilian Schier, Melanie Schaller, Bodo Rosenhahn
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
Stream4D is a training‑free, motion‑decoupled streaming 4D reconstruction framework that can be integrated into causal Transformer backbones such as StreamVGGT and Stream3R. It exploits the causal attention’s KV cache to aggregate temporal motion cues, fuses them with depth priors, and produces precise dynamic masks that separate static and dynamic regions. A soft key masking scheme then suppresses dynamic interference in attention, improving camera pose estimation and reducing ghosting in long sequences.
By Wei Zhang, Ying Feng, Mengtong Wu, Shiqiang Gong, Huaqi Zhang, Qi Zhang
arXiv:2605.23889v2 Announce Type: replace
Abstract: Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods of...
By Chong Cheng, Peilin Tao, Nanjie Yao, Guanzhi Ding, Xianda Chen, Yuansen Du, Xiaoyang Guo, Wei Yin, Weiqiang Ren, Qian Zhang, Zhengqing Chen, Hao Wang
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:2606. 31421v1 Announce Type: cross Abstract: Single-stage video object detectors are increasingly deployed in time-critical applications, yet it remains unclear whether these models genuinely reason over temporal context or merely exploit a single informative frame-a gap hidden by standard metrics, which reward correct predictions regardless of how they are reached.
By Karam Tomotaki-Dawoud, Anna Hilsmann, Peter Eisert, Sebastian Bosse
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.
Event cameras generate asynchronous, high-frequency data streams offering spatially sparse information at lower latency than traditional cameras. In principle, these properties should be ideal for the design of control policies.