).webp)
Bruce Demo
ANYMA ÆDEN
Digital Tina
For a video of length clips we obtain a sequence F = f₁,…,f_T . ATP learns a set of K pooling weights wₖ ∈ ℝᵀ via a small 1‑D convolution followed by softmax:
[ \beginaligned g_v &= \sigma(W_g v + b_g), \quad g_a = \sigma(W_g a + b_g), \ \tildev &= \textLN(v + \textSoftmax\big((g_v \odot v)(g_a \odot a)^\top / \sqrtn\big) (g_a \odot a)),\ \tildea &= \textLN(a + \textSoftmax\big((g_a \odot a)(g_v \odot v)^\top / \sqrtn\big) (g_v \odot v)), \endaligned ]
For a video of length clips we obtain a sequence F = f₁,…,f_T . ATP learns a set of K pooling weights wₖ ∈ ℝᵀ via a small 1‑D convolution followed by softmax:
[ \beginaligned g_v &= \sigma(W_g v + b_g), \quad g_a = \sigma(W_g a + b_g), \ \tildev &= \textLN(v + \textSoftmax\big((g_v \odot v)(g_a \odot a)^\top / \sqrtn\big) (g_a \odot a)),\ \tildea &= \textLN(a + \textSoftmax\big((g_a \odot a)(g_v \odot v)^\top / \sqrtn\big) (g_v \odot v)), \endaligned ] fc2 3292343
