Abstract
This paper presents a unified bag of visual word (BoW) framework for dynamic scene recognition. The approach builds on primitive features that uniformly capture spatial and temporal orientation structure of the imagery (e.g., video), as extracted via application of a bank of spatiotemporally oriented filters. Various feature encoding techniques are investigated to abstract the primitives to an intermediate representation that is best suited to dynamic scene representation. Further, a novel approach to adaptive pooling of the encoded features is presented that captures spatial layout of the scene even while being robust to situations where camera motion and scene dynamics are confounded. The resulting overall approach has been evaluated on two standard, publically available dynamic scene datasets. The results show that in comparison to a representative set of alternatives, the proposed approach outperforms the previous state-of-the-art in classification accuracy by 10%.
Keywords
Computer scienceArtificial intelligenceRepresentation (politics)PoolingSet (abstract data type)Computer visionPattern recognition (psychology)Feature (linguistics)Encoding (memory)
Affiliated Institutions
Related Publications
Dual Attention Network for Scene Segmentation
In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the self-attention mechanism. Unlike previous works that capture context...
Learning Hierarchical Features for Scene Labeling
Scene labeling consists of labeling each pixel in an image with the category of the object it belongs to. We propose a method that uses a multiscale convolutional network traine...
Coordinate Attention for Efficient Mobile Network Design
Recent studies on mobile network design have demonstrated the remarkable effectiveness of channel attention (e.g., the Squeeze-and-Excitation attention) for lifting model perfor...
Recognizing indoor scenes
We propose a scheme for indoor place identification based on the recognition of global scene views. Scene views are encoded using a holistic representation that provides low-res...
MOPED: A scalable and low latency object recognition and pose estimation system
The latency of a perception system is crucial for a robot performing interactive tasks in dynamic human environments. We present MOPED, a fast and scalable perception system for...
Publication Info
- Year
- 2014
- Type
- article
- Pages
- 2681-2688
- Citations
- 61
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
61
OpenAlex
Cite This
Christoph Feichtenhofer,
Axel Pinz,
Richard P. Wildes
(2014).
Bags of Spacetime Energies for Dynamic Scene Recognition.
, 2681-2688.
https://doi.org/10.1109/cvpr.2014.343
Identifiers
- DOI
- 10.1109/cvpr.2014.343