Update targeted manuscript analysis and selected case figure
This commit is contained in:
Xin Wang
@@ -1,11 +1,9 @@
|
||||
% Active result tables. A dash denotes an unreported or unmeasured value.
|
||||
\begin{table*}[t]
|
||||
\caption{Dense future-activity mAP (\%) at ten horizons on EasyCom and
|
||||
Ego4D. Each dataset has the same four-method comparison. EasyCom values
|
||||
are measured on Sessions~1--3; $\G$ has only archived 0.2-s and mean
|
||||
scores, and SVA awaits evaluation. Ego4D scores are pending. Dashes are unreported or unmeasured,
|
||||
not zero; intermediate scores are never interpolated. The available Omni
|
||||
rows are exploratory and not all training-matched.}
|
||||
\caption{Ten-horizon future-activity mAP (\%). EasyCom Omni rows are
|
||||
seed-0 screens; Ego4D $\G$/$\G+\A$ are three-seed means, and SVA is one
|
||||
run. The published EgoSpeak Ego4D row \cite{kim2025egospeak} uses a
|
||||
different protocol; cross-protocol differences are not paired effects.}
|
||||
\label{tab:main}
|
||||
\centering\ninept
|
||||
\renewcommand{\arraystretch}{0.91}
|
||||
@@ -17,25 +15,24 @@ Dataset / model & .2 & .4 & .6 & .8 & 1.0 & 1.2 & 1.4 & 1.6 & 1.8 & 2.0 & Mean \
|
||||
\midrule
|
||||
\multicolumn{12}{@{}l}{\emph{EasyCom}} \\
|
||||
EgoSpeak A+V & 74.20 & 68.35 & 64.31 & 61.13 & 59.77 & 58.81 & 57.50 & 57.09 & 55.95 & 54.82 & 61.19 \\
|
||||
Omni $\G$ & 73.45 & -- & -- & -- & -- & -- & -- & -- & -- & -- & 60.85 \\
|
||||
Omni $\G$ & 73.45 & 68.64 & 64.65 & 61.51 & 59.35 & 58.08 & 57.22 & 56.15 & 55.12 & 54.32 & 60.85 \\
|
||||
Omni $\G+\A$ & 81.72 & 75.92 & 70.38 & 66.46 & 63.81 & 61.37 & 60.00 & 58.32 & 56.95 & 56.16 & 65.11 \\
|
||||
Omni $\G+\A+\mathrm{SVA}$ & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- \\
|
||||
Omni $\G+\A+\mathrm{SVA}$ & 82.36 & 76.26 & 70.89 & 66.67 & 63.73 & 61.52 & 60.10 & 58.63 & 57.35 & 56.20 & 65.37 \\
|
||||
\midrule
|
||||
\multicolumn{12}{@{}l}{\emph{Ego4D}} \\
|
||||
EgoSpeak A+V & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- \\
|
||||
Omni $\G$ & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- \\
|
||||
Omni $\G+\A$ & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- \\
|
||||
Omni $\G+\A+\mathrm{SVA}$ & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- \\
|
||||
EgoSpeak GRU A+V & 76.4 & 73.0 & 70.4 & 68.5 & 67.1 & 66.3 & 65.6 & 65.2 & 64.7 & 64.4 & 68.2 \\
|
||||
Omni $\G$ & 74.72 & 72.03 & 69.81 & 68.11 & 66.81 & 65.88 & 65.21 & 64.73 & 64.35 & 63.98 & 67.56 \\
|
||||
Omni $\G+\A$ & 80.78 & 77.03 & 73.88 & 71.49 & 69.66 & 68.31 & 67.33 & 66.63 & 66.05 & 65.55 & 70.67 \\
|
||||
Omni $\G+\A+\mathrm{SVA}$ & 81.39 & 77.41 & 74.35 & 71.73 & 69.61 & 68.43 & 67.47 & 66.91 & 66.48 & 65.56 & 70.93 \\
|
||||
\bottomrule
|
||||
\end{tabular*}
|
||||
\end{table*}
|
||||
|
||||
\begin{table}[t]
|
||||
\caption{EasyCom local-vision and information-audit screens (\%). The
|
||||
upper rows are exploratory encoder-based runs; the lower rows use
|
||||
non-deployable past activity (three-seed mean $\pm$ SD). Their training
|
||||
protocols differ, so cross-section differences are not matched effects.
|
||||
Branch names are defined in Sec.~\ref{sec:method}.}
|
||||
\caption{EasyCom vision screens and privileged activity audit (\%).
|
||||
Upper rows are exploratory encoder-feature runs; lower rows use
|
||||
transcript-derived past activity unavailable at deployment (three-seed
|
||||
means). Cross-block differences are not matched model effects.}
|
||||
\label{tab:visual}
|
||||
\centering\ninept
|
||||
\renewcommand{\arraystretch}{0.92}
|
||||
@@ -46,45 +43,37 @@ Condition & mAP$_{.2}$ & Mean \\
|
||||
\midrule
|
||||
$\G+\A$ & 81.72 & 65.11 \\
|
||||
$\G+\A+$Pool & 82.03 & 65.40 \\
|
||||
$\G+\A+$SVA & -- & -- \\
|
||||
$\G+\A+$SVA & 82.36 & 65.37 \\
|
||||
$\G+\A+$TSVA & 82.38 & 65.54 \\
|
||||
\midrule
|
||||
Visibility only & $81.95{\pm}.10$ & $65.22{\pm}.05$ \\
|
||||
Delayed 1 s & $81.95{\pm}.09$ & $65.34{\pm}.05$ \\
|
||||
Visible OR & $\mathbf{86.70{\pm}.09}$ & $\mathbf{66.95{\pm}.02}$ \\
|
||||
Visibility only & 81.95 & 65.22 \\
|
||||
Delayed 1 s & 81.95 & 65.34 \\
|
||||
Visible OR & $\mathbf{86.70}$ & $\mathbf{66.95}$ \\
|
||||
\bottomrule
|
||||
\end{tabular}
|
||||
\end{table}
|
||||
|
||||
\begin{table}[t]
|
||||
\caption{Pending matched timing/context tests. Each cell will compare
|
||||
$\G$ with $\G+\A$ on common cutoffs; $\Delta$ is paired mean-mAP gain.
|
||||
PTR uses completed blocks plus the observed tail. Dashes are unmeasured.}
|
||||
\caption{EasyCom PTR context-cap screen: three-seed mean mAP (\%).
|
||||
The 8-s bank predates joint extraction; no matched $\G$ arm exists.}
|
||||
\label{tab:stream_context}
|
||||
\centering\ninept
|
||||
\renewcommand{\arraystretch}{0.92}
|
||||
\setlength{\tabcolsep}{3pt}
|
||||
\begin{tabular}{@{}llcc@{}}
|
||||
\begin{tabular}{@{}cc@{}}
|
||||
\toprule
|
||||
Group & Refresh / cap & $\G/\G+\A$ & $\Delta$ \\
|
||||
PTR context cap (s) & $\G+\A$ mean mAP \\
|
||||
\midrule
|
||||
T & Completed hold, 8 s & --/-- & -- \\
|
||||
T & PTR, 8 s & --/-- & -- \\
|
||||
\midrule
|
||||
C & PTR, 2 s & --/-- & -- \\
|
||||
C & PTR, 4 s & --/-- & -- \\
|
||||
C & PTR, 6 s & --/-- & -- \\
|
||||
C & PTR, 8 s & --/-- & -- \\
|
||||
C & PTR, 10 s & --/-- & -- \\
|
||||
C & PTR, 12 s & --/-- & -- \\
|
||||
4 & 64.81 \\
|
||||
8 & 65.18 \\
|
||||
12 & 64.74 \\
|
||||
\bottomrule
|
||||
\end{tabular}
|
||||
\end{table}
|
||||
|
||||
\begin{table}[t]
|
||||
\caption{Separate seed-0 global-only chunk screen (\%): 10 epochs, 8-s cap,
|
||||
2-FPS video. PTR is not extraction-matched to the other rows. Calls are
|
||||
processor invocations across 12 sessions, not latency.}
|
||||
\caption{Separate seed-0 global-only chunk screen (\%). PTR is not
|
||||
extraction-matched; calls are processor invocations, not latency.}
|
||||
\label{tab:chunk}
|
||||
\centering\ninept
|
||||
\renewcommand{\arraystretch}{0.95}
|
||||
|
||||
Reference in New Issue
Block a user