HP-VSR-ResFiLM adds a single residual FiLM modulation block conditioned on head pose to a CNN visual encoder, yielding WER of 25.0% on LRS2 and 33.2% on LRS3 under standard training conditions.
Sparsevsr: Lightweight and noise robust visual speech recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Pruning small-magnitude weights from pre-trained LLMs causes monotonic irreversible performance degradation on difficult downstream tasks, supporting the Junk DNA Hypothesis that these weights hold essential knowledge.
citing papers explorer
-
Head-Pose-Aware Visual Speech Recognition with FiLM Modulation
HP-VSR-ResFiLM adds a single residual FiLM modulation block conditioned on head pose to a CNN visual encoder, yielding WER of 25.0% on LRS2 and 33.2% on LRS3 under standard training conditions.
-
Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMs
Pruning small-magnitude weights from pre-trained LLMs causes monotonic irreversible performance degradation on difficult downstream tasks, supporting the Junk DNA Hypothesis that these weights hold essential knowledge.