Recognizing Interactions in Video

Taj, Murtaza; Cavallaro, Andrea

doi:10.1007/978-3-642-11756-5_2

Cited by 5 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table III also presents the variation in the performance 2 The same MLT is because ID change(s) for both trackers have occurred in the same tracks. of the trackers in terms of standard deviation (σ) values for different measures.…”

Section: Evaluation Of Trackersmentioning

confidence: 99%

Measures of Effective Video Tracking

Nawaz

Poiesi

Cavallaro

2014

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Abstract-To evaluate multi-target video tracking results, one needs to quantify the accuracy of the estimated target-size and the cardinality error as well as measure the frequency of occurrence of ID changes. In this paper we survey existing multi-target tracking performance scores and, after discussing their limitations, we propose three parameter-independent measures for evaluating multi-target video tracking. The measures take into account target-size variations, combine accuracy and cardinality errors, quantify long-term tracking accuracy at different accuracy levels, and evaluate ID changes relative to the duration of the track in which they occur. We conduct an extensive experimental validation of the proposed measures by comparing them with existing ones and by evaluating four state-of-the-art trackers on challenging real-world publicly-available datasets. The software implementing the proposed measures is made available online to facilitate their use by the research community.

show abstract

Section: Evaluation Of Trackersmentioning

confidence: 99%

Measures of Effective Video Tracking

Nawaz

Poiesi

Cavallaro

2014

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some works also applied constraints to the number of involved objects, e.g. four individuals [5] or two people [3].…”

Section: Introductionmentioning

confidence: 99%

“…detection of face-to-face con versations in a meeting [2] and detection of bag stealing or unat tended luggage in video surveillance [3]) use prior knowledge about the scene and detection is performed based on multi-modal inputs, e.g. speech, facial expressions, pose and gaze [4].…”

Section: Introductionmentioning

confidence: 99%

Detecting group interactions by online association of trajectory data

Chen

Cavallaro

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

Self Cite

View full text Add to dashboard Cite

We propose a method for detecting group interactions for groups of varying number of objects. We model each object as a moving agent with a direction-aware interest map and group interactions as mutual interests between objects. After grouping objects into unit interac tions individually in each frame, we solve the temporal association problem by tracking group interaction over consecutive frames. Op timal grouping is obtained by finding the maximum weight spanning tree of a directed graph formed by objects and their potential inter actions. Experimental results show that our method obtained around 80% recalling rates on two publicly available datasets.

show abstract

Multi-Target Tracking in Video

Poiesi

Cavallaro

2014

Academic Press Library in Signal Processing: Volume 4 - Image, Video Processing and Analysis, Hardware, Audio, Acoustic and Spe

View full text Add to dashboard Cite

Recognizing Interactions in Video

Cited by 5 publications

References 34 publications

Measures of Effective Video Tracking

Measures of Effective Video Tracking

Detecting group interactions by online association of trajectory data

Multi-Target Tracking in Video

Contact Info

Product

Resources

About