Copertina

Can masking background and object reduce static bias for zero-shot action recognition?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fukuzawa, Takumi, Hara, Kensho, Kataoka, Hirokatsu, Tamaki, Toru
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Human Action Recognition without Human
di: Kataoka, Hirokatsu, et al.
Pubblicazione: (2016)

M3DDM+: An improved video outpainting by a modified masking strategy
di: Murakawa, Takuya, et al.
Pubblicazione: (2026)

Fine-grained length controllable video captioning with ordinal embeddings
di: Nitta, Tomoya, et al.
Pubblicazione: (2024)

Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding
di: Torimi, Kohei, et al.
Pubblicazione: (2025)

Multi-model learning by sequential reading of untrimmed videos for action recognition
di: Kamiya, Kodai, et al.
Pubblicazione: (2024)

Formula-Supervised Visual-Geometric Pre-training
di: Yamada, Ryosuke, et al.
Pubblicazione: (2024)

Simple Visual Artifact Detection in Sora-Generated Videos
di: Sugiyama, Misora, et al.
Pubblicazione: (2025)

Query matching for spatio-temporal action detection with query-based object detector
di: Hori, Shimon, et al.
Pubblicazione: (2024)

Industrial Synthetic Segment Pre-training
di: Mae, Shinichi, et al.
Pubblicazione: (2025)

S3OD: Towards Generalizable Salient Object Detection with Synthetic Data
di: Kupyn, Orest, et al.
Pubblicazione: (2025)

Action tube generation by person query matching for spatio-temporal action detection
di: Omi, Kazuki, et al.
Pubblicazione: (2025)

Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models
di: Zhu, Peifei, et al.
Pubblicazione: (2024)

Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes
di: Otsuka, Daichi, et al.
Pubblicazione: (2025)

Leveraging LLMs with Iterative Loop Structure for Enhanced Social Intelligence in Video Question Answering
di: Mori, Erika, et al.
Pubblicazione: (2025)

Shift and matching queries for video semantic segmentation
di: Mizuno, Tsubasa, et al.
Pubblicazione: (2024)

Reflective Dialogue between Teacher and Solver Agents for Video Question Answering
di: Murakawa, Takuya, et al.
Pubblicazione: (2026)

HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
di: Tateno, Masatoshi, et al.
Pubblicazione: (2025)

AnimalClue: Recognizing Animals by their Traces
di: Shinoda, Risa, et al.
Pubblicazione: (2025)

AgroBench: Vision-Language Model Benchmark in Agriculture
di: Shinoda, Risa, et al.
Pubblicazione: (2025)

PowerCLIP: Powerset Alignment for Contrastive Pre-Training
di: Kawamura, Masaki, et al.
Pubblicazione: (2025)

Primitive Geometry Segment Pre-training for 3D Medical Image Segmentation
di: Tadokoro, Ryu, et al.
Pubblicazione: (2024)

Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation
di: Yoshihashi, Ryota, et al.
Pubblicazione: (2023)

Two-stream joint matching method based on contrastive learning for few-shot action recognition
di: Deng, Long, et al.
Pubblicazione: (2024)

Can VLMs be used on videos for action recognition? LLMs are Visual Reasoning Coordinators
di: Lunia, Harsh
Pubblicazione: (2024)

The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks
di: Calabrese, Carmela, et al.
Pubblicazione: (2024)

FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation
di: Yamamoto, Yukinori, et al.
Pubblicazione: (2026)

MoExDA: Domain Adaptation for Edge-based Action Recognition
di: Sugimoto, Takuya, et al.
Pubblicazione: (2025)

Shot2Tactic-Caption: Multi-Scale Captioning of Badminton Videos for Tactical Understanding
di: Ding, Ning, et al.
Pubblicazione: (2025)

Disentangling Static and Dynamic Information for Reducing Static Bias in Action Recognition
di: Kobayashi, Masato, et al.
Pubblicazione: (2025)

BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioning
di: Ding, Ning, et al.
Pubblicazione: (2026)

Online pre-training with long-form videos
di: Kato, Itsuki, et al.
Pubblicazione: (2024)

MoireDB: Formula-generated Interference-fringe Image Dataset
di: Matsuo, Yuto, et al.
Pubblicazione: (2025)

Can the accuracy bias by facial hairstyle be reduced through balancing the training data?
di: Ozturk, Kagan, et al.
Pubblicazione: (2024)

Constant Rate Scheduling: A General Framework for Optimizing Diffusion Noise Schedule via Distributional Change
di: Okada, Shuntaro, et al.
Pubblicazione: (2024)

3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds
di: Yamada, Ryousuke, et al.
Pubblicazione: (2025)

Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning
di: Takama, Yusaku, et al.
Pubblicazione: (2025)

On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process
di: Iwase, Shun, et al.
Pubblicazione: (2025)

CLIP-like Model as a Foundational Density Ratio Estimator
di: Uchiyama, Fumiya, et al.
Pubblicazione: (2025)

Egocentric zone-aware action recognition across environments
di: Peirone, Simone Alberto, et al.
Pubblicazione: (2024)

3DFlowRenderer: One-shot Face Re-enactment via Dense 3D Facial Flow Estimation
di: Nijhawan, Siddharth, et al.
Pubblicazione: (2024)