Merge branch 'main' of http://182.92.86.220:8300/wx44wx/icassp2027-experiment

manuscript/main/main.tex

@@ -329,47 +329,55 @@ configuration, trainable parameter counts, and inference latency.}
 We first retain dense future-activity evaluation for direct comparison with
 EgoSpeak, reporting AP at the 0.2--2.0~s horizons and their mean mAP.
 
-For dense-only models, behavioral evaluation begins with an explicitly
-activity-derived event proxy rather than treating wearer voice activity as a
-semantic event detector. Following the prediction-region principle used by
-VAP~\cite{ekstedt2022vap}, every adjudicated item contributes one score from a
-fixed 0.6-s (three-frame) causal decision region. A positive uses the three
-source frames immediately preceding its corrected behavior anchor. An
-independently mined hard negative uses the first three source frames after its
-opportunity begins; a raw wearer boundary relabeled as a hard negative instead
-uses the same pre-boundary region as a positive. Items without a complete
-three-frame region are excluded and counted. The longer interval supplied to
-the annotator is evidence context only and is never a model-scoring window.
+For dense-only models, behavioral evaluation is opportunity-conditioned and
+uses the model's original wearer-activity forecasts rather than treating them
+as semantic intent probabilities. An entry opportunity begins at a reviewed
+non-wearer release. It resolves positively when the wearer enters, or
+negatively when the same non-wearer resumes or a different non-wearer takes the
+next floor. From the first causal 5-Hz state that observes the release, the
+entry score is the maximum projected wearer probability before that competing
+resolution, capped at 2.0~s. Positive entries without a reviewer-selected
+release are reported as unanchored and excluded from this matched-opportunity
+analysis; they remain available to the separate raw-onset analysis.
 
-At each decision frame, we follow the target-aligned forecast tensor
-diagonally to recover the wearer probabilities emitted at that same causal
-source time. We average the 0.6--2.0-s horizons to obtain a sustained wearer-
-activity score. This mean is the entry proxy, and one minus the mean is the
-INT-yield proxy. Max-pooling the three decision-frame scores gives exactly one
-score per positive event or hard-negative opportunity. This construction can
-capture sustained activity versus a brief vocalization, but it cannot by
-itself establish semantic floor intent; in particular, wearer backchannels and
-within-turn pauses remain deliberately difficult negatives. A later linear
-event probe, if used, is fit only on training-side annotations and compared at
-matched capacity across representations, following the separated downstream-
-probe logic of MuVAP~\cite{qi2026muvap}.
+An INT opportunity begins when a non-wearer starts while the wearer holds the
+floor. It resolves positively when the reviewed behavior is an INT-yield, and
+negatively when the non-wearer contribution is a backchannel or failed
+takeover and the wearer retains the floor. The yield score is the maximum of
+one minus the projected wearer probability over the next 0.2--0.6~s, censored
+strictly at the competing non-wearer offset. All prediction values are read
+diagonally from one causal source row of the target-aligned forecast tensor.
+No input after the observed action outcome is used. For current INT-positive
+annotations, which do not select a competing onset explicitly, the
+implementation uses the latest supplied non-wearer interval crossing the
+wearer offset and surfaces cases with multiple eligible intervals for audit.
+
+The headline entry hard negatives are same-speaker mid-turn pauses and other-
+to-other transfers. Wearer backchannels are not pooled into headline false-
+entry rate: their high wearer probability is correct under the dense training
+target. We instead retain entry-versus-backchannel as a separate semantic-
+selectivity diagnostic. Thus, the semantic annotations define which matched
+opportunities are evaluated, while every model is scored solely through the
+same EgoSpeak-compatible dense output. A capacity-matched downstream probe,
+following MuVAP~\cite{qi2026muvap}, is secondary and is not needed for this
+zero-shot activity-derived comparison.
 
 \textbf{False-positive scoring rule.}
-A false positive is a hard-negative opportunity whose fixed-region proxy score
+A false positive is a hard-negative opportunity whose opportunity score
 exceeds the frozen threshold, regardless of whether the wearer subsequently
-exhibits an onset or offset. Max-pooling means that multiple high-scoring
-decision frames still count as one false-positive opportunity. Thus, false-positive
-evaluation includes conversational situations in which the correct wearer
-behavior is to remain silent or retain the floor.
+exhibits an unrelated later onset or offset. Each opportunity contributes one
+score, and competing-risk censoring prevents later conversational outcomes
+from changing its label. Thus, false-positive evaluation includes situations
+in which the correct wearer behavior is to remain silent or retain the floor.
 
 We report threshold-free proxy AP for entry and INT. The headline behavioral
 operating point additionally reports false-positive rate at matched recall
 $R=0.8$; thresholds are selected independently for entry and INT from training-
 side out-of-fold predictions. The other-to-other hard-negative subset tests
 whether local visual evidence specifically reduces erroneous wearer action
-scores during multiparty floor transfers. \todo{Freeze the 0.6-s decision
-window and 0.6--2.0-s aggregation range using training-side data, run window
-sensitivity analysis, and verify identical event denominators across methods.}
+scores during multiparty floor transfers. \todo{Freeze the 2.0-s entry and
+0.6-s yield caps using training-side data, audit selected-release and competing-
+onset coverage, and verify identical censored/valid denominators across methods.}
 
 A deployment-style committed-event analysis with one-to-one matching and
 signed latency is secondary and is omitted unless a threshold, persistence,
@@ -394,8 +402,8 @@ verify identical targets, causal validity, and evaluation.}
 
 \begin{table}[t]
 \caption{Confirmatory EasyCom results. Entry and INT false-positive rates use
-the fixed-region activity-derived proxy at matched recall $R=0.8$; E/I AP is
-the corresponding event-balanced proxy AP.}
+the opportunity-conditioned activity score at matched recall $R=0.8$; E/I AP
+is the corresponding event-balanced opportunity AP.}
 \label{tab:main}
 \centering
 \small
@@ -427,7 +435,7 @@ evidence primarily improves \todo{the interpretation supported by the data}.
 \textbf{Annotated behavior.}
 At matched wearer-entry recall $R=0.8$, the proposed adapter reduces entry FPR
 from \todo{$X$} to \todo{$Y$}; at matched INT-yield recall, it changes INT FPR
-from \todo{$A$} to \todo{$B$}. Its entry/INT activity-proxy APs are
+from \todo{$A$} to \todo{$B$}. Its entry/INT opportunity APs are
 \todo{$E/I$}. These recall-matched opportunity error rates test whether lower
 scores on confusing floor situations are obtained without suppressing
 legitimate entry or yield events.