Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks375 from public data
- 2,128
- Early versus late fusion in semantic video analysis1,010
It is shown by experiment on 184 hours of broadcast video data and for 20 semantic concepts, that late fusion tends to give slightly better performance for most concepts, however, for those concepts where early fusion performs better the difference is more significant.
- The challenge problem for automated detection of 101 semantic concepts in multimedia691
The challenge problem for generic video indexing is introduced to gain insight in intermediate steps that affect performance of multimedia analysis methods, while at the same time fostering repeatability of experiments.
- Multimodal Video Indexing: A Review of the State-of-the-art574
A unifying and multimodal framework is put forward, which views a video document from the perspective of its author, which forms the guiding principle for identifying index types, for which automatic methods are found in literature.
- VideoLSTM convolves, attends and flows for action recognition489
A new architecture for end-to-end sequence learning of actions in video, called VideoLSTM, which introduces motion-based attention and demonstrates how the attention from VideoLSTM can be used for action localization by relying on just the action class label.
- Concept-Based Video Retrieval452
This paper presents a component-wise decomposition of such an interdisciplinary multimedia system, covering influences from information retrieval, computer vision, machine learning, and human–computer interaction and lays down the anatomy of a concept-based video search engine.
- 401
- 378
- 305
- 258
- 249
- The MediaMill TRECVID 2004 Semantic Video Search Engine240
The 2008 edition of the TRECVID bench- mark has been the most successful MediaMill participation to date, resulting in the top ranking for both concept de- tection and interactive search, and a runner-up ranking for automatic retrieval.
- 235
- 225
- 210
- Learning to Learn with Variational Information Bottleneck for Domain Generalization206
A probabilistic meta-learning model for domain generalization is introduced, in which classifier parameters shared across domains are modeled as distributions, which enables better handling of prediction uncertainty on unseen domains.
- Learning tag relevance by neighbor voting for social image retrieval202
A novel algorithm that scalably and reliably learns tag relevance by accumulating votes from visually similar neighbors is proposed, and treated as tag frequency, learned tag relevance is seamlessly embedded into current tag-based social image retrieval paradigms.
- PointMixup: Augmentation for Point Clouds201
It is proved that the PointMixup finds the shortest path between two point clouds and that the interpolation is assignment invariant and linear, which allows to introduce strong interpolation-based regularizers such as mixup and manifold mixup to the point cloud domain.
- Online Action Detection200
A realistic dataset composed of 27 episodes from 6 popular TV series and an evaluation protocol for fair comparison is introduced, showing this is a challenging problem for which none of the methods provides a good solution.
- 200
- 190
- Skeleton-Contrastive 3D Action Representation Learning189
This paper proposes inter-skeleton contrastive learning, which learns from multiple different input skeleton representations in a cross-contrastive manner, and contributes several skeleton-specific spatial and temporal augmentations which further encourage the model to learn the spatio-temporal dynamics of skeleton data.
- 178
- Socializing the Semantic Gap173
A two-dimensional taxonomy is introduced to structure the growing literature, understand the ingredients of the main works, clarify their connections and difference, and recognize their merits and limitations.
- Objects2action: Classifying and Localizing Actions without Any Video Example172
Objects2action is a semantic word embedding that is spanned by a skip-gram model of thousands of object categories that proposes a mechanism to exploit multiple-word descriptions of actions and objects and demonstrates how to extend the zero-shot approach to the spatio-temporal localization of actions in video.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.