"Even though two similar targets simultaneously occur in this video, ROLO tracks the correct target as the detection module inherently feeds the LSTM unit with spatial constraint. Note that between frame 47-60, YOLO fails in detection but ROLO does not lose the track." is mentioned in the page 7 of paper.
And my question is "why doesn't YOLO detect the left side person when the right side person was occlude ? "
Can someone help me? Thank you!
"Even though two similar targets simultaneously occur in this video, ROLO tracks the correct target as the detection module inherently feeds the LSTM unit with spatial constraint. Note that between frame 47-60, YOLO fails in detection but ROLO does not lose the track." is mentioned in the page 7 of paper.
And my question is "why doesn't YOLO detect the left side person when the right side person was occlude ? " Can someone help me? Thank you!